21

Statistics and Probability
21.1 INTRODUCTION

Statistics is as old as human society itself. It is difficult to imagine any facet of our life untouched by numerical data. Modern society is essentially data-oriented. It is, therefore, essential to know how to extract useful information from such data. This is the primary objective of statistics. Statistics concerns itself with the collection, presentation, and drawing of inferences from numerical data that vary. In a singular sense, statistics is used to describe the principles and methods that are employed in collection, presentation, analysis, and interpretation of data. These devices help to simplify the complex data and make it possible for a common man to understand it without much difficulty. The human mind is unable to assimilate complicated data at a stretch. Statistical methods make these figures intelligible and readily understandable. In a plural sense, statistics is considered as a numerical description of the quantitative aspect of things. Definition. Statistics is the science that deals with methods of collecting, classifying, presenting, comparing, and interpreting numerical data in order to throw light on any sphere of enquiry.
21.2 VARIABLE (OR VARIATE)

A quantity that can vary from one individual to another is called a variable or variate, e.g., heights, weights, ages, wages of people, rainfall records of cities, etc. Quantities that can take any numerical value within a certain range are called continuous variables, e.g., as a child grows, his/her height takes all possible values from 50 cm to 100 cm. Quantities that are incapable of taking all possible values are called discrete or discontinuous variables, e.g., the number of children in a family are positive integers 1, 2, 3, etc. (no value between any two consecutive integers).
21.3 FREQUENCY DISTRIBUTIONS

Consider the grades obtained by 60 students in mathematics: 38, 11, 40, 0, 26, 15, 5, 45, 7, 32, 2, 18, 42, 8, 31, 27, 4, 12, 35, 15, 0, 7, 28, 46, 9, 16, 29, 34, 10, 7, 5, 1, 17, 22, 35, 8, 36, 47, 11, 30, 19, 0, 16, 14, 16, 18, 41, 38, 2, 17, 42, 45, 48, 28, 7, 21, 8, 28, 5, 20. The data does not give any useful information. It is rather confusing. These are called raw data or ungrouped data.

1146 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________

We would like to bring out certain salient features of this data. If we express the data in ascending or descending order of magnitude, this does not reduce the bulk of the data. We condense the data into classes or groups as below: (i) Determine the range of the data, i.e., the difference between the largest and smallest numbers occurring in the data. Here the range = 48 – 0 = 48. (ii) Decide upon the number of classes or groups into which raw data is to be grouped. There are no hard and fast rules for this. The insight of the experimentor determines this number. However, the number of classes should not be less than 5 or more than 30. With a smaller number of classes accuracy is lost and with a larger number of classes the computations become tedious. Let us make the number of classes = 7 here. (iii) Divide the range by the desired number of classes to determine the approximate width or size of class interval. If the quotient is a fraction, take the next integer. In the above example, 48 or 7. the size of the class interval is 7 As far as possible, classes should be of the same size. (iv) Using the size of the interval, set up the class limits, making sure that the minimum and the maximum numbers occurring in the data are included in some class. As far as possible, openend classes (a < x < b) should be avoided since they create difficulty in analysis and interpretation. Boundaries of each class are selected in such a way that there is no ambiguity as to which class a particular item of the data belongs. (v) The observations corresponding to the common point of two classes should always be included in the higher class, e.g., if 20 is an element of the data and 10–20 and 20–30 are two classes, then 20 is to be set in the class 20–30 and not 10–20. That is to say every class should be regarded as open to the right. (vi) Take each item from the data, one at a time, and place a tally mark (/) opposite the class to which it belongs. Tally marks are recorded in bunches of five. Having occurred four times, the fifth occurrence is represented by setting a cross-tally ( \ or / ) on the first four tallies ( |||| or |||| ). This technique facilitates the counting of the tally marks at the end.

(vii) The count of tally marks in a particular class provides us with the frequency in that class. The word “frequency” is derived from “how frequently” a variable occurs. (viii) Grades are called the variable (x) and the number of students in a class is known as the frequency ( f ) or class frequency of the variable. (ix) The total of all frequencies must equal the number of observations in the raw data. (x) The table displaying the manner in which frequencies are distributed over various classes is called the frequency table. (xi) We are often interested in knowing, at a glance, the number of observations less than a particular value. This is done by finding cumulative frequency. The cumulative frequency corresponding to a class is the sum of frequencies of that class and of all classes prior to that class. (xii) The table displaying the manner in which cumulative frequencies are distributed is called the cumulative frequency table. Using the above steps, we have the following cumulative frequency table for the example under consideration.

21.3 FREQUENCY DISTRIBUTIONS 1147 ________________________________________________________________________________________________________

Class interval Tally marks (grades x) (number of students) 0–7 7–14 14–21 21–28 28–35 35–42 42–49 Total |||| |||| |||| |||| || |||| |||| || |||| |||| ||| |||| || |||| ||

Frequency (f) 10 12 12 4 8 7 7 60

Cumulative Frequency 10 22 34 38 46 53 60

ILLUSTRATIVE EXAMPLES

Example 1. The weights in grams of 50 apples picked at random from a market are as follows: 106, 107, 76, 82, 109, 107, 115, 93, 187, 195, 123, 125, 111, 92, 86, 70, 126, 68, 130, 129, 139, 119, 115, 128, 100, 186, 84, 99, 113, 204, 111, 141, 136, 123, 90, 115, 98, 110, 78, 90, 107, 81, 131, 75, 84, 104, 110, 80, 118, 82. Form the grouped frequency table by dividing the variate range into intervals of equal width, each corresponding to 20 gms in such a way that the mid-value of the first class corresponds to 70 gms. Sol. Mid-value of first class = 70 ⎫ (given) ⎬ Width of each class = 20 ⎭ ∴ The first class interval is (70 – 10) – (70 + 10) i.e., 60 – 80.

Weight in grams
60–80 80–100 100–120 120–140 140–160 160–180 180–200 200–220 Total

No. of apples
|||| |||| |||| ||| |||| |||| |||| || |||| |||| | ||| |

Frequency
5 13 17 10 1 0 3 1 50

Example 2. Form an ordinary frequency table from the following table:

Grades Above Above Above 0 10 20

No. of Students 40 30 25

Grades Above Above Above 30 40 50

No. of Students 18 12 0

o Students of 22 30 38 Gra ades 0– –10 10– –20 20– –30 30– –40 40– –50 50– –60 21.4 No of Student ( f ) o. Gr rades 0– –10 10– –20 20– –30 30– –40 40– –50 No of Student ( f ) o. ts 40 4 – 30 = 10 0 30 3 – 25 = 5 25 2 – 18 = 7 18 – 12 = 6 12 – 0 = 12 2 ample 3.1148 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ Sol. . ts 5 7–5=2 13 – 7 = 6 22 2 – 13 = 9 30 3 – 22 = 8 38 3 – 30 = 8 “E EXCLUSIVE AND “INC E” CLUSIVE” C CLASS-INTE ERVALS Clas ss-intervals of the type { x : a ≤ x < b} = [a. The f r e following da are classi ata ified on this basis. N of Studen nts 5 7 13 Grades Belo ow Belo ow Belo ow 40 50 60 No. For an ordina frequenc table from the followin rm ary cy m ng: Exa Grades G Below B Below B Below B Sol. b) ar called “ex re xclusive” sin they exc nce clude the upper limit of the class. 10 20 30 No.

. It is a series of observations of the form Class Interval : a1 − a2 a2 − a3 .5–249. the exclusive method of classification should be adopted. b ] are called “inclusive” since they include the upper limit of the class. Income ($) 50–99 100–149 150–199 200–249 250–299 No. 21. Adjustment. we have to make an adjustment.5 THREE TYPES OF SERIES In this chapter. The adjusted classes would 2 then be as follows: Income ($) No.5 60 99. to ensure continuity and to get correct class-limits.5–99. .. x3 .5. It is a series of observations of the form x : x1 . (b) Discrete Series. For the purpose of further calculations in statistical work. . 100 − 99 In the above example. x3 . an − an +1 f f1 f2 fn : . of people 49. xn .5 16 249.5 7 The size of the class interval is 50.e. the mid-point of each class is taken to represent the class.5–149. A person whose income is $100 is included in the class $100–$150. of people 50–100 88 100–150 70 150–200 52 200–250 30 250–300 23 In this method.21. . . Class-intervals of the type { x : a ≤ x ≤ b} = [ a. . .99. the upper limit of one class is the lower limit of the next class. x2 . there are 88 people whose income is from $50 to $99. The following data are classified on this basis. In this example.5 THREE TYPES OF SERIES 1149 ________________________________________________________________________________________________________ Income ($) No. To convert inclusive class-intervals into exclusive ones. f n (c) Continuous Series. xn f : f1 .5–199. x2 .. . . . f 2 . . Find the difference between the lower limit of the second class and the upper limit of the first class. Divide it by 2. . we will come across the following three types of series: (a) Individual Observations (i. Subtract the value obtained from all the lower limits and add the value to all the upper limits. f3 . . of people 60 38 22 16 7 However. where frequencies are not given).5–299. ..5 38 149. Form x : x1 . the adjustment factor is = .5 22 199. .

Some important types of graphs are given below: (A) Histogram In drawing the histogram of a given grouped frequency distribution: (a) Mark off along the x-axis all the class intervals on a suitable scale. A better perspective can be had by representing the frequency distribution graphically since graphs. 100. 110. Sol. . 85. 55. 110. 85. . We can have different scales for the two axes. f n . 55. . are eye-catching and leave a more lasting impression on the mind of the observer. then mi = form Mid -value Frequency m: f : m1 . m2 . 60. Width of the class interval = ⎜ ⎝ 7 ⎠ Wts. 75. ai + ai +1 and the above series takes the 2 The mid-value of the ith class may also be denoted by xi . m3 . f2 . of oranges No. 50. 65. a continuous series is reduced to the form of a discrete series. 30. 70. ILLUSTRATIVE EXAMPLES Example 1. The determination of scale depends upon our convenience and the type and nature of the data. . The scale or scales should be so chosen as to fit the size of graphpaper and to hold all the figures of the data. 40.6 GRAPHICAL REPRESENTATION A frequency distribution when represented by means of a graph makes the unwieldy data intelligible. The weights (in grams) of 40 oranges picked at random from a basket are as follows: 45. the facts may be misrepresented. 65. (110) – min. of oranges Frequency (in gms. 35. 70. (30) = 80 Let the number of class intervals = 7 ⎛ 80 ⎞ or ⎟ 12. 75. . 30. 70. 60. if drawn attractively. 85. 55. (c) It must not be assumed that the scale for both the axes will be the same. . (If class-intervals are equal. A diagram with all these rectangles is called a histogram. . 95. 80. 70. 40. . 21. 75. Another disadvantage is that by taking different scales. (d) Construct rectangles with the class-intervals as bases and heights proportional (if the class intervals are equal) to the frequencies. 100. then each = 1 cm is quite suitable. 90. 70. Graphs are a good visual aid. Represent the data by means of a histogram. Thus. 60.) 30–42 42–54 54–66 66–78 78–90 90–102 102–114 Total |||| || |||| |||| ||| |||| |||| |||| |||| || 7 4 8 9 5 5 2 40 . But graphs do not give accurate measurements of the variable as are given by the tables. 40. 45. 80.) (b) Mark frequencies along the y-axis on a suitable scale.1150 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Thus. 75. Range = max. mn f3 . 100. f1 . 45. if mi is the mid-point of the ith class.

148. 6. t cy on draw the his stogram and fred quency p polygon. . 144. 2. . 147. 173. 6. 135.21. on the x-axis. n Exa ample 2. ∴W Width of clas interval = ⎜ ss ⎝ 7 ⎠ t Weight (to the nearest pound) o t 102–113 3 113–124 4 124–135 5 135–146 6 146–157 7 157–168 8 168–179 9 Total Tally mar rks Frequency F 1 1 4 14 12 5 3 40 | | |||| |||| |||| |||| |||| |||| || |||| ||| . 165. mber of class = 7 ses Num ⎛ 74 ⎞ or ⎟ 11. 145. 136. 145. 135. . 168.6 GRA APHICAL REP PRESENTATIO ON 1151 __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ The histogram of the above frequency d o distribution is given here e: (B) Frequency Polygon distribution with equal class-interv vals. 164. 119 154. 157. 144. Sol. 142. min. 138. 102. . 156. 140. 126 138. a frequ uency polygon is For a grouped frequency d obtained by joining the middle p t points of the upper sides (tops) of th adjacent rectangles o the e he of histogram by means of straight lines. i. 135.e. 176 163. 147. 9. 146. 142 150. the mid-points at each en are e s nd joined to the immediately lower and higher m mid-points at zero freque t ency. Range of ra data = ma (176) – m (102) = 74 aw ax. 132. 150. 149. 140. To co m omplete the polygon. 128. The following t e table gives th weights ( the neare pound) of 40 students at a he (to est f s university Construct a frequenc distributio with 7 classes and d y. 146. 152.. 158. 125.

F Frequency po olygon: show dotted. Plot the points w the low limits of the classes as abscissae and with wer f e esponding more-than cu m umulative fre equency as ordinates. (An o It ogive usually means a le ess-than ogiv ve. Plot th points wit the upper limits of the classes as a he th e abscissae an the nd (i) L correspon nding less-th cumulative frequenc as ordinat Join the points by a freehand sm han cy tes. o students 4 (+ 6 = )10 (+ 10 = ) 20 0 (+ 20 = ) 40 0 (+ 18 = ) 58 8 (+ 2 = ) 60 Gra ades more-than 10 20 30 40 50 60 70 No. There are two type of ogives. of stud dents 60 6 (– 4 = ) 5 56 (– 6 = ) 5 50 (– 10 = ) 4 40 (– 20 = ) 2 20 (– 18 = ) 2 (– 2 = ) 0 . I is a rising curve.1152 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ The histogram and frequenc polygon a shown he a cy are ere: (H Histogram: re ectangles.) (ii) More-than ogive.F.” distrib i bution and t then into a “ “more-than C C. s Grades less-than n 20 30 40 50 60 70 of No.” distributi ion. It i a falling cu t an is urve. of students 20 18 2 Let us convert it first into a “less-than C.) wn e y the (C) Cumulative Frequency Curve or t Ogive ined by plot tting the cum mulative freq quency is ca alled a cumu ulative frequ uency The curve obtai ronounced oj jive). curve or an ogive (pr Less-than og give. mooth curve to get the less-t than ogive.F. Con nsider the fol llowing frequency distrib bution: Grades s 10–20 20–30 30–40 No. es . Jo the poin by a free oin nts ehand the corre smooth c curve to get the more-tha ogive. of students 4 6 10 Gra ades 40– –50 50– –60 60– –70 No.

(60 3). 4 12 2 23 3 38 8 50 0 56 6 59 9 More-tha an C. 59). and jo nts (l0. It is of is ften desirabl to define quantitative the char le ely racteristics o the of frequency distributio y on. Plot joining th by freeh hem hand.F. 50). ( . (50. oining them by freehand.7 CO OMPARISO OF FREQ ON QUENCY DISTRIBUTIO ONS Whe two or more differe series of the same t en m ent f type are com mpared. 12). 23). 9). 6). (60. 21).F F. of stud dents 12 6 3 tting the poi ints (10. and 0. 56 (70. (50. 59 55 47 36 21 9 3 No. 59). (30. 0. 36). (30. ned han Plot tting the poin (0. o students of 4 8 11 15 12 6 3 Less-than C. s Grades 0–10 10–20 0 20–30 0 30–40 0 40–50 0 50–60 0 60–70 0 No. 0. (40 38). o students of 4 8 11 15 Grad des 40– –50 50– –60 60– –70 No.7 COM MPARISON OF FREQUENCY DISTRIBUTI F IONS 1153 __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ Exa ample 3. (20 47). ( 55). 21. Dr raw the two ogives for the followi distribut o ing tion showing the numb of ber grades of 59 students f s: Grades s 0–10 10–20 0 20–30 0 30–40 0 Sol. the smooth fal lling curve o obtained is m more-than og give. tabu ulation of o observations i not sufficient. 4). 3 (40.21. (20. . the sm mooth rising c curve obtain is less-th ogive.

the groups tabulated are still too large for their characteristics to be readily grasped. Short Cut Method. n n 2. + ( xn − a) = sum of the deviations of the variate x from a n = number of observations. . Median 5.M.. where most of the items of the series cluster. . xn then A. Measures of this kind are called measures of dispersion. possibly in the center.8 MEASURES OF CENTRAL TENDENCY Tabulation arranges facts in a logical order and helps their understanding and comparison. but a value somewhere between these two limits. .8. Arithmetic Average or Mean 4. . 21. . xn f : f1 . x2 . Harmonic Mean 3. . Direct Method. Direct Method. .) Shifting the origin to an arbitrary point a. . . (Shift of origin. But often. in the value of the variate x around which they center. If x : x1 . f n . + f n xn Σ fx = N f1 + f 2 + . Measures of central tendency or measures of location (also popularly called averages) serve this purpose. . + f n . Mode In the case of Individual Observations (i. . x2 . . In the case of a Discrete Series: 1. . called the Assumed Mean Σd x = Σ( x − a) = ( x1 − a ) + ( x2 − a ) + . f 2 . . . There are five types of averages in common use: 1. What is desired is a numerical expression that summarizes the characteristic of the group. + xn 1 = Σx. .1 Arithmetic Mean 2. a = arbitrary number. . the formula 1 1 x = Σx becomes x − a = Σ( x − a ) n n 1 or x = a + Σd x where d x = x − a n x= Here. + f n = Σf f1 x1 + f 2 x2 + . . where frequency is not given): 1. If the frequency distribution is x : x1 . i. . Geometric Mean We shall take them one by one. 21.e. x is given by x1 + x2 + . (ii) They may differ in the extent to which observations are scattered about the central value. .1154 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ There are two fundamental characteristics in which similar frequency distributions may differ: (i) They may differ in measures of location or central tendency.e. A figure that is used to represent a whole series should neither have the lowest value nor the highest in the series.. . x= then where N = f1 + f 2 + . . Such figures are called Measures of Central Tendency (or averages).

+ f n = Σ f . of students 5 9 17 29 45 Grades Below Below Below Below Below 60 70 80 90 100 No. the mid-values of the class intervals are considered as x and then the above formulae are applied. h Weighted Arithmetic Mean. w2 . we may attach weights to them w1 .. In the case of Continuous Series having equal class intervals. . (Shift of origin. say of width h.8 MEASURES OF CENTRAL TENDENCY 1155 ________________________________________________________________________________________________________ 2. Note. Find the mean from the following data: Grades Below Below Below Below Below 10 20 30 40 50 No.e. the formula 1 1 x = Σfx becomes x − a = Σf ( x − a ) N N 1 x = a + Σfd x . . N = f1 + f 2 + . Step Deviation Method). . + wn Σw ILLUSTRATIVE EXAMPLES Example 1. . we get Σfx hΣfu =a+ N N Σfu N or x = a+h where u= x−a . . . we use a different formula (Shift of origin and change of scale. If the variate-values are not of equal importance. The weighted mean xw is defined as xw = w1 x1 + w2 x2 + . where d x = x − a or N 1 Thus x = a + Σfd x where a = assumed mean N Σ fd x = Σ f ( x − a) = f1 ( x1 − a ) + f 2 ( x2 − a) + . + wn xn Σwx = (i. of students 60 70 78 83 85 . If the frequencies are given in terms of class intervals. Short Cut Method. . . write w for f ). . x−a Let u= then x = a + hu h ∴ Σfx = Σf (a + hu ) = aΣf + hΣfu Dividing both sides by N = Σf . + f n ( xn − a) = sum of the products of f and the deviation of the corresponding variate x from a. . . wn as measures of their importance. w1 + w2 + .21. .) Shifting the origin to an arbitrary point a.

. h = 10] ⎟ N ⎝ 86 ⎠ 112 = 55 − = 48.9. . N Property II. The mean of 200 items was 50. Let dx be the deviation of the variate x from the mean x . n = 200 Σx ∴ Σx = nx x= Since n Using the incorrect value of x .41. Later on it was discovered that two items were misread as 92 and 8 instead of 192 and 88.1156 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Sol. 2. where N = Σ f . Let z be the sum of the squares of the deviations of the given values from an arbitrary point a (say). Find the correct mean. n. Proof. . Incorrect Σx = 200 × 50 = 10000 ∴ Corrected value of Σx = 10000 − (92 + 8) + (192 + 88) = 10180 Corrected Σx 10180 = = 50. The algebraic sum of the deviations of all the variates from their arithmetic mean is zero. i = 1. . Here the incorrect value of x = 50. The sum of the squares of the deviations of a set of values is minimum when taken about the mean. Proof. . The frequency distribution table can be written as: Grades Mid values (x) f x − 55 u= 0–10 10–20 20–30 30–40 40–50 50–60 60–70 70–80 80–90 90–100 5 15 25 35 45 55 65 75 85 95 5 4 8 12 16 15 10 8 5 2 N = Σ f = 85 – 50 – 40 – 30 – 20 – 10 0 10 20 30 40 x − 55 10 –5 –4 –3 –2 –1 0 1 2 3 4 fu – 25 – 16 – 24 – 24 – 16 0 10 16 15 8 Σ fu = −56 Σ fu ⎛ −56 ⎞ = 55 + 10 × ⎜ [Here a = 55. Let the frequency distribution be xi / fi . then dx = x − x ∴ Σ fd x = Σ f ( x − x ) = Σ fx − x Σ f = Nx − Nx = 0 ∵x = Σ fx . Sol. 17 Example 2. Correct mean = 200 n Here x = a + h Properties of the Arithmetic Mean Property I.

... . . (Mean of the composite series... and so on. ....... Σ f = N⎥ ⇒ Nx − aN = 0 ⎣ ⎦ ⇒ x −a =0 ( ∵ N = Σ f ≠ 0) ⇒ a=x n d 2z = −2∑ f (−1) = 2Σ f = 2N > 0 da 2 i =1 Hence z is minimum when a = x .21. . .... k). + xknk ) n1 + n2 + . . then the mean x of the whole distribution obtained by combining the k distributions is given by n x + n x + . . . . ... + nk xk Σ ni xi x= 1 1 2 2 = i Σ ni n1 + n2 + . . x13 .. + x2 n2 ) + .. k) are the arithmetic means of k distributions with respective frequencies ni (i = 1. .. + nk ) is given by x= = ( x11 + x12 + .. .. + nk Also i Proof. Let x11 . . . . . + xknk ) ⎪ nk ⎭ x1 = .⎪ ⎪ 1 ⎪ xn = ( xk1 + xk2 + . . .. . x21 . ... x22 ..... Property III.8 MEASURES OF CENTRAL TENDENCY 1157 ________________________________________________________________________________________________________ ⇒ Let z = ∑ f ( x − a)2 .. + nk Σ ni i . . . .. + nk n1 x1 + n2 x2 + .. x1n1 be the variables of the first distribution.. .. . . x12 . + x2 n2 ) ⎪ n2 ⎬ . + nk xkk Σ ni xi = i n1 + n2 + . . dz d 2z z will be minimum when = 0 and >0 da da 2 n n dz Now = ∑ 2 f ( x − a ) ⋅ (−1) = −2∑ f ( x − a ) da i = 1 i =1 dz ∴ = 0 ⇒ −2Σ f ( x − a ) = 0 da ⇒ Σ fx − aΣ f = 0 Σ fx ⎡ ⎤ ⎢ ∵ x = N . x2n2 be the variables of the second distribution... .. ... . .. ... + x1n1 ) + ( x21 + x22 + .) If xi (i = 1.. + x1n1 ) ⎪ n1 ⎪ 1 ⎪ x2 = ( x21 + x22 + .. 2. ... i =1 n We have to show that z is minimum when a = x . 2. . ( A) The mean x of the whole distribution of size (n1 + n2 + .. .. . .. Then by definition 1 ⎫ ( x11 + x12 + .. . + ( xk1 + xk2 + .

For an ungrouped frequency distribution. f = frequency of the median class N = Σf . The mean annual salaries paid to male and female employees were $52000 and $42000 respectively.8. the middle value. C = cumulative frequency of the class preceding the median class. there are two middle values ⎜ ⎟ and ⎜ + 1⎟ . ⎝ 2 ⎠ ⎛n⎞ ⎛n ⎞ (b) When n is even.2 Median 1. we get 50000 = x= 1 1 Using p1 + p2 100 or 520 p1 + 420 p2 = 50000 or 260 p1 + 210 p2 = 25000 260 p1 + 210(100 − p1 ) = 25000 [Using (1)] or 50 p1 = 25000 – 21000 = 4000 ∴ p1 = 80 and p2 = 100 − 80 = 20 or Hence the percentage of males and females is 80 and 20 respectively. thus. Sol. a potential average.e. l = lower limit of the median class. 4. . The median is. i.. 21. if the n values of the variate are arranged in ascending or descending order of magnitude. ⎝2⎠ ⎝2 ⎠ The arithmetic mean of these two values gives the median. the median is given by the formula. When the observations are arranged in the order of their size. The median is the central value of the variable when the values are arranged in ascending or descending order of magnitude. 2. For the computation of a median. . the median is obtained by considering cumulaN +1 N +1 tive frequencies. h⎛N ⎞ Median = l + ⎜ − C ⎟ f⎝2 ⎠ where. The mean annual salary paid to all employees of a company was $50000. For a discrete frequency distribution. Find the cumulative frequency just ≥ . the median is the value of that item that has an equal number of observations on either side. Let p1 and p2 represent the percentage of males and females respectively. where the median class is the class corresponding N to the cumulative frequency just ≥ 2 h = width of the median class. Determine the percentage of males and females employed by the company. it is necessary that the items be arranged in ascending or descending order. ⎜ ⎟ value gives the median. . The 2 2 corresponding value of x is the median. The median divides the distribution into two equal parts. 3. For a grouped frequency distribution.1158 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Example 3. Find where N = Σfi . th th th . (1) Then p1 + p2 = 100 Mean annual salary of all employees ( x ) = $50000 = $52000 Mean annual salary of all males ( x1 ) Mean annual salary of all females ( x2 ) = $42000 p x + p2 x2 52000 p1 + 42000 p2 . ⎛ n +1 ⎞ (a) When n is odd.

Q3 = l + ⎜ f ⎝4 f ⎝ 4 ⎠ ⎠ (b) Deciles. Grades in Math Grades in Physics Roll Nos. we find out the medians of both the series. . ⎜ f ⎝ 100 ⎠ (The 50th percentile P50 is the median. the letters l. Quartiles are those values of the variate that divide the total frequency into four equal parts. (Q2 being the median. C have been used in the same sense in which they have been used in the formula for the median. (a) Quartiles.) (c) Percentiles. . When the lower half before the median is divided into two equal parts. ILLUSTRATIVE EXAMPLES Example 1. .) The formulae for computation are Q1 = l + h⎛N h ⎛ 3N ⎞ ⎞ − C⎟ ⎜ − C ⎟ .8 MEASURES OF CENTRAL TENDENCY 1159 ________________________________________________________________________________________________________ 5. f ⎝ 10 ⎠ D4 = l + h ⎛ 4N ⎞ − C⎟. . These are the values of the variate that divide the total frequency into a number of equal parts. Grades in Math Grades in Physics : : : : : : 1 53 58 11 25 10 2 54 55 12 42 42 3 52 25 13 33 15 4 32 32 14 48 46 5 30 26 15 72 50 6 60 85 16 51 64 7 47 44 17 45 39 8 46 80 18 33 38 9 35 33 19 65 30 10 28 72 20 29 36 In which subject is the level of knowledge of the students higher? Sol. D1 = l + h⎛N ⎞ ⎜ − C⎟. and Percentiles. second. percentiles. Partition values. Percentiles are those values of the variate that divide the total frequency into 100 equal parts. Deciles are those values of the variate that divide the total frequency into 10 equal parts. D1. . . deciles. . ⎜ f ⎝ 100 ⎠ P72 = l + h ⎛ 72N ⎞ − C ⎟ etc. ⎜ f ⎝ 10 ⎠ D7 = l + h ⎛ 7N ⎞ − C⎟ ⎜ f ⎝ 10 ⎠ (The fifth decile D5 is the median. second. . . To find out the subject in which the level of knowledge of the students is higher. .21. . Deciles. N. The subject for which the median value is higher will be the subject in which the level of knowledge of the students is higher.) In the above formulae for Quartiles. then P9 = l + h ⎛ 9N ⎞ − C⎟. D2. Below are given the grades obtained by a group of 20 students in a certain class in mathematics and physics: Roll Nos. the value of the dividing variate is called the Lower Quartile and is denoted by Q1. Let us arrange the grades in ascending order of magnitude. f. The value of the variate dividing the upper half into two equal parts is called the Upper Quartile and is denoted by Q3. denote respectively the first. denote respectively the first. the median being that value of the variate that divides the total frequency into two equal parts. If P1. i. P2. . .

Median grades in physics = A. of sizes of 10th and 11th items = 2 Since the median grades in mathematics are greater than the median grades in physics.5. Example 2. 8 18 29 45 65 90 105 114 120 9 6 Sol.F. = A. N +1 is 65 and the value of x corresponding to 2 . 11 12 13 14 15 16 17 18 19 20 Grades in Math 46 47 48 51 52 53 54 60 65 72 Grades in Physics 42 44 46 50 55 58 64 72 80 85 Number of items in each case = 20 (even) Median grades in Mathematics ⎛ 20 ⎞ ⎛ 20 ⎞ = A.5.M. of sizes of 10th and 11th items = 2 39 + 42 = 40. The cumulative frequency distribution table is given below: The cumulative frequency just greater than C. Hence the median is 5. the level of knowledge in mathematics is higher.F. Obtain the median for the following frequency distribution: x: 1 f: 8 x 1 2 3 4 5 6 7 8 9 Here N = 120 ∴ N +1 = 60.M. No. 65 is 5.5 2 2 10 3 11 4 16 f 8 10 11 16 20 25 15 9 6 5 20 6 25 7 15 8 9 C.M. No.1160 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ S. of sizes of ⎜ ⎟ th and ⎜ + 1⎟ th items ⎝ 2 ⎠ ⎝ 2 ⎠ 45 + 46 = 45. 1 2 3 4 5 6 7 8 9 10 Grades in Math 25 28 29 30 32 33 33 35 42 45 Grades in Physics 10 15 25 26 30 32 33 36 38 39 S.

94.25 − 60) f ⎝4 24 ⎠ 22. 24 (iii) Calculation of upper quartile Q3 3N 747 = = 186. f = 71. l = 30 4 h = 10. of students 94 127 198 249 C. Find the median. of students ( f ) 15 20 25 24 10 33 71 51 (i) Calculation of Median N = 124.94 = 30.41 = 68. C = 94 2 h ⎛N 10 ⎞ Median = l + ⎜ − C ⎟ = 50 + (124. No. C = 60 ∴ (ii) Calculation of lower quartile Q1 ∴ Q1 = l + h⎛N 10 ⎞ ⎜ − C ⎟ = 30 + (62. h = 10.41.5 − 94) f ⎝2 33 ⎠ 305 = 50 + = 50 + 9. we reconstruct the C.75 ∴ upper quartile class is 60 − 70 4 4 l = 60. f = 33. table with class intervals.5 = 60 + = 60 + 8. C = 127 ∴ Q3 = l + h ⎛ 3N 10 ⎞ − C ⎟ = 60 + (186.5 = 30 + = 30 + .F.F.75 − 127) ⎜ f ⎝ 4 71 ⎠ 597.8 MEASURES OF CENTRAL TENDENCY 1161 ________________________________________________________________________________________________________ Example 3. l = 50. 15 35 60 84 94 127 198 249 Sol. From the above table. and upper quartiles from the following table: Grades Below 10 Below 20 Below 30 Below 40 Grades 0–10 10–20 20–30 30–40 40–50 50–60 60–70 70–80 Here N = 249 No.5 ∴ median class is 50 − 60.25 ∴ lower quartile class is 30 − 40. 71 .21.24 = 59.24 33 N = 62. h = 10. f = 24. lower. of students 15 35 60 84 Grades Below 50 Below 60 Below 70 Below 80 No.

(d) Where the mode is ill-defined.8. Calculation of the Mode. Mode.3 Mode 1. mode is the value of x corresponding to maximum frequency. the value of the mode is determined by the method of grouping (illustrated in the examples below). In other words. the mode or modal value of the distribution is that value of the variate for which frequency is maximum. In case fm – f1 < 0 or 2fm – f1 – f2 = 0. h is the width. and mode coincide. i. its value can be ascertained by the formula Mode = 3 Median – 2 Mean This measure is called the empirical mode. While applying the above formula. they should first be made equal on the assumption that the frequencies are equally distributed throughout the class. and fm is the frequency of the model class. use the formula Mode = l + where Δ1 ×h Δ1 + Δ 2 Δ1 = f m − f1 and Δ 2 = f m − f 2 . (a) In the case of discrete frequency distribution.e. It is the point of maximum frequency or the point of greatest density. Mode is the value that occurs most frequently in a set of observations and around which the other items of the set cluster densely. (b) In the case of a continuous frequency distribution. ILLUSTRATIVE EXAMPLES Example 1. Calculate the mode from the following frequency distribution: Size (x) : Frequency ( f ) : 4 2 5 5 6 8 7 9 8 12 9 14 10 14 11 15 12 11 13 13 . it is necessary to see that the class-intervals are of the same size. the mean. median. and f1 and f2 are the frequencies of the classes preceding and succeeding the modal class respectively..1162 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 21. (c) For a symmetrical distribution. 2. the mode is given by the formula: Mode = l + f m − f1 ×h 2 f m − f1 − f 2 where l is the lower limit. But in any one (or more) of the following cases: (i) if the maximum frequency is repeated (ii) if the maximum frequency occurs in the very beginning or at the end of the distribution (iii) if there are irregularities in the distribution. If they are unequal. where the method of grouping also fails.

the Column ns I II III IV V VI 8. frequencies of column I are combine three by t f ed three. 9. 10 10. . In column V. 12 1 Size of item having max. the ma aximum freq quency is wri itten in bold black type. leave the firs frequency of column I and combin the others two by two. b umns. 9 10. Sinc the item 10 occurs a m ce 1 maximum nu umber of tim (i. ne mn w le against every maximum item of colu y umns I to V we VI.. frequencies of column I are combine two by tw f ed wo. In column II. All operat tions are don on colum I. leave the firs frequency of column I and combin the others three by thr l st y ne s ree. Now we frame another tabl in which a write dow the corre wn esponding s size or sizes. 5 tim mes mes). leave the firs two freque l st encies in col lumn I and c combine the others three e by three.21. The size ( that occu the maxi (x) urs imum numb of ber times is t mode. 10 10.e. In all these colu Note. Method of Grouping: f original freq o quencies are written. In column IV. l st y ne s . 11 11. In column VI. freque ency 11 11 planation: Exp In column I. hence the mode is 10. 9 9. 9 9. In column III.8 MEA ASURES OF CENTRAL TEN C NDENCY 1163 __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ Sol.

of students 10 5 8 7 20 . f n times respectively and N = given by G = ( x1f1 x2f2 . Hence the modal class is 16–20. . But the actual limits of this class are 15.1164 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Example 2. f 2 . .5 + = 18. . . . i =1 i n then the G.83. .) of n individual observations x1. .M. l = 15.4 Geometric Mean Geometric Mean. h = 5 f m − f1 32 − 16 × h = 15. of candidates : : : : 1–5 7 26–30 18 6–10 10 31–35 10 11–15 16 36–40 5 16–20 32 41–45 1 21–25 24 Sol. x2.5 + ×5 2 f m − f1 − f 2 64 − 16 − 24 16 10 × 5 = 15. (a) The geometric mean (G. .M. . f1 = 16. x is taken to be the value corresponding to the mid-points of the class-intervals.5. Find the mode of the following: Grades No. . is 1 1 n ( f1 log x1 + f 2 log x2 + . xnfn )1/ N Taking logarithms of both sides log G = ∑f. . Compute the geometric mean from the following data: Grades 0–10 10–20 20–30 30–40 40–50 No. . xn occur f1 .5 + 21. . . . . + log xn ) = ∑ log xi n n i =1 Taking logarithms of both sides log G = ∴ ⎡1 n ⎤ G = antilog ⎢ ∑ log xi ⎥ ⎣ n i =1 ⎦ (b) If x1 . f m = 32. . x2 .8.5–20. . x2 . . of candidates Grades No. f 2 = 24. Example. 24 3 ∴ Mode = l + = 15.5. . xn )1/ n 1 1 n (log x1 + log x2 + . + f n log xn ) = ∑ f i log xi N N i =1 ⎡1 n ⎤ G = antilog ⎢ ∑ f i log xi ⎥ ⎣ N i =1 ⎦ (c) In the case of a continuous frequency distribution. Here the greatest frequency 32 lies in the class 16–20. xn ( xi ≠ 0) is the nth root of their product. . Thus G = ( x1 . .

Find the harmonic mean of the following data: Grades (out of 150) No..21.. .6532 f log x 6.008 20   f x . of Students (f) 10 5 8 7 20 50 log x 0.1761 1. .8805 11. .025 60 5 . . x2 .8087 33. 1 x f x 10 2 .9900 5. .+ ∑ xn n i = 1 xi x1 x2 If x1 . 21.050 40 6 .83. . Thus.150 .3585 N 50 G = antilog 1.8.200 . The harmonic mean of a number of observations is the reciprocal of the arithmetic mean of the reciprocals of the given values.017 120 4 . x2 . f n respectively.085 .1832 10. f 2 .3979 1. Grades 0–10 10–20 20–30 30–40 40–50 Mid-values (x) 5 15 25 35 45 No.9264 Σ f log x = = 1. xn is 1 n = H= n . .3585 = 22.8 MEASURES OF CENTRAL TENDENCY 1165 ________________________________________________________________________________________________________ Sol. the harmonic mean H of n observations x1 .6990 1.100 20 3 . .032 . of students 10 2 20 3 40 6 60 5 120 4 Sol. .150 . + xnn n i =1 i In the case of class-intervals.9264 log G = 1 67.5441 1. .5 Harmonic Mean Harmonic Mean.0640 67. N = ∑ fi = f f f f 1 i =1 ∑ xi x11 + x22 + . . ILLUSTRATIVE EXAMPLES Example 1. xn (none of them being zero) have the frequencies f1 . . 1 1 1 1 1 + +. . . x is taken to be the mid-value of the class-interval.617 . then the harmonic mean is given by n 1 N H= n .

28. the harmonic mean is the proper average. 510. 630. 790. 440.] 4. 690. 310. 28.0.9. 740. and 400 km/hr respectively.8. 380. f .1. 26.0. 750. 27.2. 26. 300. 670.0. The following are the monthly rents (in dollars) of 40 stores. 24. 25. 30. 370. 3.4. 24.5. 430. 4 Average speed = = 192 km/hr. 200.6. 26. 28.0. 820.1. Scores 90–99 80–89 70–79 60–69 50–59 40–49 30–39 5. 490. 24. 29. 27.0. 27.7. of students 4 1 3 1 2 Frequency 2 12 22 20 14 3 1 . 28. Mid-values of class intervals of size 5 are given. Tabulate the data by grouping in intervals of $8. of students 5 13 12 11 8 Grades 50–60 60–70 70–80 80–90 90–100 No. 26.5.6. When equal distances are covered with unequal speeds. 770. 2. The minimum temperature in (°C) for Anytown for the month of July.2. 25. 470. 670. 750. 28. 570. 25. 420. 25.5. 620. 24. 640.9. 27. 28. 820. 30. 25. = N 20 = = 32. 30. 520.3.0. 540. An airplane flies along the four sides of a square at speeds of 100. 27. Represent the following distribution by an ogive: Grades 0–10 10–20 20–30 30–40 40–50 No. 770.0. ∴ 1 1 1 1 + + + 100 200 300 400 TEST YOUR KNOWLEDGE 1.5. 540.7. 620. 370. Represent the following distribution by a (i) histogram and (ii) frequency polygon.0. Construct a frequency distribution table for it.1166 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ H.5. 720. 360.2.4. 480. 25.0. 740. 840. 380.617 Σx Example 2.2.4. 31. 810. What is the average speed of the airplane in its flight around the square? Sol. 440. 750. 2006 as reported by the Meteorological Department is given below. Draw a histogram representing the following frequency distribution: Monthly Wages Number of Workers (in $) 15 2 20 20 25 26 30 16 35 9 40 4 45 3 [Hint.M. 470.8. 840. 27.

physics 59. Age Group Frequency 80–89 2 70–79 2 60–69 6 50–59 20 Calculate the arithmetic mean of the data. . 5. The average height of a group of 25 children was calculated to be 78. The frequencies of values 0. of students 80 77 72 65 55 43 Grades Above 60 Above 70 Above 80 Above 90 Above 100 No. and chemistry 55. 12. . mathematics 63. From the following data calculate the missing frequency: No. 5. Calculate the correct average. nC2qn–2p2. The frequency distribution gives the ages of the people interviewed. of pills 4–8 8–12 12–16 16–20 20–24 No.21. Find the weighted mean if weights 2. of people cured 9 17 6 4 The average number of pills to cure a person is 20. nC1qn–lp. Compute the arithmetic mean for the following data: Height (in cm): No. . . Show that the mean is np. n of a variable are given by qn. 3 are allotted to the subjects. Find the class intervals if the arithmetic mean of the following distribution is 33 and assumed mean is 35. 1. of people cured 11 13 16 14 ? No. . of students 28 16 10 8 0 8. Find the average grades of students from the following data: No. pn where p + q = 1. 13.4 cm. A candidate obtains the following percentage in an examination: english 60. 2.8 MEASURES OF CENTRAL TENDENCY 1167 ________________________________________________________________________________________________________ 6. Two hundred people were interviewed by a public opinion polling agency. . Class interval 0–1 1–3 3–5 5–10 10–15 Frequency 8 8 10 12 18 Age Group 40–49 30–39 20–29 10–19 Frequency 56 40 42 32 9. . . of pills 24–28 28–32 32–36 36–40 No. 14. Calculate the arithmetic mean from the following data: Class interval 15–25 25–28 28–30 30–45 45–60 Frequency 11 10 9 8 6 10. It was later discovered that one value was misread as 69 cm instead of the correct value of 96 cm. Step deviation (u) Frequency ( f ) : : –3 5 –2 10 –1 25 0 30 1 20 2 10 11. of people: Grades Above 0 Above 10 Above 20 Above 30 Above 40 Above 50 219 2 216 4 213 6 210 10 207 11 204 7 201 5 198 4 195 1 7. 1. history 75. .

385. 1200. 250.1168 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 15. 222. What is the mean of the remaining 100 students? 16. find the ratio of the number of students in class A to the number in class B.5 10. 782. Find the average bonus paid per employee.5–13. . The mean of the top 100 of them was found to be 70 and the mean of the last 100 was known to be 20.4 and that of all students in class B is 71. Find the median from the following table: x: f: 5 1 7 2 9 7 11 9 13 11 15 8 17 5 19 4 20. and so on up to exceeding 1400 but not exceeding 1500.5–11. The following are the monthly salaries in dollars of 30 employees of a firm: 910 1390 1260 1190 1000 870 650 770 990 950 1080 1270 860 1480 1160 760 690 880 1120 1180 890 1160 970 1050 950 800 860 1060 930 1350 The firm gave bonuses of 100. of families 15 10 8 7 23. 1180.5 11. 17.5 21. the following are the population figures in thousands of 10 cities: 2000. 400. Find the median. If the average of both classes combined is 70. Calculate the mean and median from the following table: Class interval 6. 200. determine the missing frequencies using the median formula. Find the median.5 7. An incomplete frequency distribution is given as follows: Variable 50–60 60–70 70–80 Total Frequency ? 25 18 229 Given that the median value is 46. quartiles. The mean grades obtained by 300 students in the subject of statistics is 45. 450. 1123. and 500 to employees in the respective salary groups: exceeding 600 but not exceeding 700. 300.5–7. of families 6 9 11 14 20 Frequency 12 30 ? 65 Monthly Rent ($) 1200–1400 1400–1600 1600–1800 1800–2000 No. 18.5 9. 1785. 350.5 8. exceeding 700 but not exceeding 800. 1500. Compute the median from the following data: Mid-value 115 125 135 145 155 Monthly Rent ($) 200–400 400–600 600–800 800–1000 1000–1200 Variable 10–20 20–30 30–40 40–50 Frequency 6 25 48 72 116 Mid-value 165 175 185 195 Frequency 60 38 22 3 Frequency 5 12 25 48 32 6 1 22.5–9. 7th decile.5–8.5–10.5–12. According to the census of 2006. the average grade of all students in class A is 68.5 12. 150. 560. 19. and 85th percentile from the following data: No. In a certain examination.2.

of workers 4 44 38 28 6 No. Find the mode of the following frequency distribution: Size Frequency Grades 0–10 10–20 20–30 30–40 Monthly wages (in $) 500–700 700–900 900–1100 1100–1300 1300–1500 : : 1 3 2 8 3 15 4 23 5 35 6 40 7 32 Grades 40–50 50–60 60–70 70–80 Monthly wages (in $) 1500–1700 1700–1900 1900–2100 2100–2300 8 28 9 20 10 45 11 14 12 6 26. Find the mode and median from the following table: No. 4th decile.] 28.21.] 25.8 MEASURES OF CENTRAL TENDENCY 1169 ________________________________________________________________________________________________________ 24. then the geometric n log G 1 + n2 log G 2 mean G of the combined series is given by log G = 1 . Calculate the mode of the following distribution: No. lower and upper quartiles. G1 and G2 the geometric means of two series respectively. Expenditure No. : : 11 3 12 7 13 8 14 5 15 2 32. n1 + n2 31. To find any partition value. Compute the geometric mean of the following data: : : 10 2 15 3 18 5 20 6 25 4 30. The grades obtained by 25 students in a test are given below: Grades No. of students Find the harmonic mean. Compute the harmonic mean of the following data: Class 0–10 10–20 20–30 30–40 40–50 Frequency 4 6 10 7 3 . Calculate the missing frequencies. Use the method of grouping for finding the modal class. If n1 and n2 are the sizes. of families x y : : 0–100 14 100–200 ? 200–300 27 300–400 ? 400–500 15 29. An incomplete distribution of families according to their expenditure per week is given below. Here the class-intervals are not all equal. The median and mode for the distribution are $250 and $240 respectively. of students 10 12 18 7 Grades 14–18 18–20 20–25 25 and above No. of workers 8 12 2 2 [Hint. Find the median. and 60th percentile for the following distribution: Grades 0–4 4–8 8–12 12–14 No. of students 5 8 4 6 [Hint. of students 35 20 6 3 27. of students 2 18 30 45 No. there is no need to make them equal.

B. It can .8 years 60. 21.9 DISPERSION N A m measure of central tende c ency by itse can exhi only elf ibit one of the importa characte ant eristics of distribution.54 cm 0–10. .1170 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ 33. represent a series only as well as a sing figure ca It is inadequa to give us a complete idea of the distribution It must ate s e n. .5. 20–30.75 79. 45 6 250. for these differences. 51. . 207. 31.M.5 thousands ($) 110 781.33. Such v variation is c called dispersio or spread or scatter o variability Thus.8 $975.03 8. matter whether we measure tempe m erature in Centigrade or Fahr renheit. and from C to A at 50 km/hr. disp on d or y.97 36. 18. Three cities A. .125. k m 0 mine 34. such mea asure is Disp persion. B to C at 40 km/hr. and C are equidistant fr A e rom each other A woman dri r.10 MEASURES OF DISPERSION M S The following are the measu of dispe a ures ersion: (a) R Range (b) Quartile de ) eviation or se emi-inter-qu uartile range (c) A Average (or mean) devia ation (d) Standard d ) deviation. w es clustered around or scattered aw from the point of ce d way e entral tenden ncy.80. w e Answers A 6. er Therefore. 16. 6. . be suppo orted and su upplemented by some o d other measur One res. 11. 10–20. 23.20 38. .00 12. 29. the valu of the va ues ariate 6 differ fro 100 but the differenc is small. 00. 24. Two or more frequency d o distributions may have exactly identical averages but even then they may differ mark y kedly in several w ways. In distribution B. the two dist om h s tributions w widely differ from each othe in their formation. 22. ives from A to B at 30 km/hr from r. persion is th extent to which the v he values are dispe ersed about the central v t value. 30–40. 18. . while studying a distribution it is equally important to know how the variate are e n. 13. Determ her average speed.M. Ran = L – S. 1333.36 14 $275 153. 33. L+S . 17. Largest and S = Smalles st L −S Coe efficient of th Range = he . Although the A. he g Dist tribution A : Dist tribution B : 75 10 85 20 2 95 30 105 70 11 15 18 80 125 290 600 = 100.3 km/hr 9. is the same. 10. Ran is the di nge ifference bet tween the ex xtreme values of the varia ate. In d distribution A. Furthe analysis is therefore. 1 40–50. 27. 36. 25. The A. ean Me edian = 9.89. 9. the ite are wid om t ce ems dely scattered and d lie far fro the mean. Show that in finding the a n arithmetic mea of a set of readings on a thermometer it does not m an f r. 50–60 1151. 12. of ea distribut ach tion is 21.6 . (a) R Range. 10. 17. 15. 20. . 28. 19. 18. 140 00. 32. essential to account er s. where L = L nge .87.30 1600 0.7 __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ 21.48 cm 45 13 34.57 7. 12. 26. 35. 240 16. it does matter which scale we use. but tha in finding the geometric m at mean. Consider th following example: . t o gle an.63% 3:4 Me = 9.

.e.10 MEASURES OF DISPERSION 1171 ________________________________________________________________________________________________________ It is easily understood and computed. . i.. If x1 . i. of students ( f ) 4 6 8 12 7 2 C. 2 2 2 (c) Average Deviation or Mean Deviation. It is not a reliable measure of dispersion.e. (b) Quartile Deviation. . . . x3 . But it suffers from the drawback that it depends exclusively on the two extreme values. 2 It is definitely a better measure of dispersion than range as it makes use of 50% of the data. of students : 0–5 4 5–10 6 10–15 8 15–20 12 20–25 7 25–30 2 Sol.75 ∴ Class of Q1 is 5 − 10 4 h⎛N 5 5 × 5.75 ⎞ = 9. Quartile Deviation = 1 (Q3 − Q1 ). No. f 2 . Coefficient of the Quartile Deviation = Q3 − Q1 . . f 3 .21. is called the semi2 inter-quartile range or the quartile deviation..F. .79 Q1 = l + ⎜ − C ⎟ = 5 + (9. But since it ignores the other 50% of the data. f n times respectively and N = median) is given by ∑f. Q3 + Q1 Example.95.25 − 18) = 15 + = 19. Calculate the quartile deviation of the grades of 39 students in statistics given below: : Grades No. 1 (Q3 – Q1).79) = × 9.90 = 4. .75 − 4) = 5 + f ⎝4 6 6 ⎠ 3N = 29. xn occur f1 .25 ∴ Class of Q3 is 15 − 20 4 h ⎛ 3N 5 5 × 11. it is also not a reliable measure of dispersion. 4 10 18 30 37 39 N = 9. The difference between the upper and lower quartiles.69 − 9.69 Q3 = l + ⎜ f ⎝ 4 12 12 ⎠ 1 1 1 Quartile deviation = (Q3 − Q1 ) = (19. The cumulative frequency table is given below: Grades 0– 5 5–10 10–15 15–20 20–25 25–30 Here N = Σ f = 39.25 ⎞ − C ⎟ = 15 + (29. Q3 – Q1 is known as the inter-quartile range and half of it. x2 . i =1 i n the mean deviation from the average A (usually mean or .

5 13 28 44 50 x − Md 23 13 3 7 17 115 104 45 112 102 478 N = 25 ∴ The median class corresponds to c. Thus σ =+ 1 Σ fi ( xi − x ) 2 . of students : 0–10 5 10–20 8 Sol. median class is 20–30 2 h⎛N 10 ⎞ Median M d = l + ⎜ − C ⎟ = 20 + (25 − 13) = 20 + 8 = 28 f ⎝2 15 ⎠ 1 478 = 9. i. denoted by s.f. Find the mean deviation from the median of the following frequency distribution: : Grades No.1172 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Mean deviation = 1 n ∑ fi xi − A . Coefficient of Mean Deviation = Mean Deviation .F. N Note. Mid-value 5 15 25 35 45 f 5 8 15 16 6 50 C. Short-cut methods for calculating Standard Deviation ( σ ). This renders it useless for further mathematical treatment. it is a better measure of dispersion than range or quartile deviation. The square of the standard deviation σ 2 is called variance. Thus s=+ 1 Σ fi ( xi − A) 2 N When the deviations are taken from the mean x .e. The root-mean square deviation.. is defined as the positive square root of the mean of the squares of the deviations from an arbitrary origin A. Average from which it is calculated 20–30 15 30–40 16 40–50 6 f x − Md Example. Root-Mean Square Deviation.56 marks. 28. N i =1 where xi − A represents the modulus or the absolute value of the deviation (xi – A). But some artificiality is created due to ignoring the signs of the deviations (xi – A). Since the mean deviation is based on all the values of the variate. the root-mean square deviation is called the standard deviation and is denoted by the Greek letter σ . Mean deviation from median = Σ f x − M d = N 50 (d) Standard Deviation. .

21.10 MEASURES OF DISPERSION 1173 ________________________________________________________________________________________________________

(i) Direct Method

σ=

1 Σ fi ( xi − x ) 2 N 1 1 1 1 Σ f i ( xi2 − 2 xi x + x 2 ) = Σ fi xi2 − 2 x ⋅ Σ f i xi + x 2 ⋅ Σ f i N N N N

σ2 =

(taking the constants x , x 2 outside the summation sign) = ⇒ 1 1 1 Σ fi xi2 − 2 x ⋅ x + x 2 ⋅ ⋅ N = Σ fi xi2 − x 2 N N N 1 Σ fi xi2 − x 2 = N 1 ⎛1 ⎞ Σ fi xi2 − ⎜ Σ fi xi ⎟ . N ⎝N ⎠
2

σ=

(ii) Change of Origin Let the origin be shifted to an arbitrary point a. Let d = x – a denote the deviation of variate x from the new origin d = x−a ⇒ d = x −a

d −d = x−x

σx =

1 Σ f ( x − x )2 = N

1 Σ f (d − d ) 2 = σ d N

∴ The S.D. remains unchanged by shift of origin.

σx = σd

1 ⎛1 ⎞ Σ fd 2 − ⎜ Σ fd ⎟ . N ⎝N ⎠

2

Note. In the case of series of individual observations, if the mean is a whole number, take a = x . In the case of discrete series, when the values of x are not equidistant, take a somewhere in the middle of the x-series.

(iii) Shift of Origin and Change of Scale (Step Deviation Method) 1 Let the origin be shifted to an arbitrary point a. Let the new scale be times the original h scale. Let u = x−a then hu = x − a ⇒ hu = x − a ∴ h(u − u ) = x − x h 1 1 1 σx = Σ f ( x − x )2 = Σ fh 2 (u − u ) 2 = h Σ f (u − u ) 2 = hσ u N N N

which is independent of a but not h. Hence the S.D. is independent of the change of the origin but not of the change of scale. 1 ⎛1 ⎞ Σ fu 2 − ⎜ Σ fu ⎟ σ x = hσ u = h N ⎝N ⎠
2

Note. In the case of discrete series, when the values of x are equidistant at intervals of h or in the case of continuous series having equal class intervals of width h, use the Step Deviation Method.

1174 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________

Relation between σ and s By definition, we have
s2 = 1 1 Σ f i ( xi − a) 2 = Σ fi ( xi − x + x − a) 2 N N 1 = Σ fi ( xi − x + d ) 2 where d = x − a N 1 = Σ fi [( xi − x ) 2 + d 2 + 2d ( xi − x )] N 1 2d 2d d2 d2 2 2 (0) = Σ fi ( xi − x ) + Σ fi + Σ fi ( xi − x ) = σ + ⋅ N + N N N N N [∵ Σ f i ( xi − x ) = algebraic sum of the deviations from mean = 0] =σ 2 + d2 s2 = σ 2 + d 2 ∵ d 2 ≥ 0 Hence ∴ s2 ≥ σ 2 Clearly s2 is least when d = 0, i.e., x = a ∴ Mean square deviation (s2) and consequently the root-mean square deviation (s) is least when the deviations are measured from the mean. Hence standard deviation is the least possible root-mean square deviation.
21.11 RELATIONS BETWEEN MEASURES OF DISPERSION

4 4 (standard deviation) = σ 5 5 2 2 Semi-interquartile range = (standard deviation) = σ . 3 3 Mean Deviation =
21.12 COEFFICIENT OF DISPERSION

Whenever we want to compare the variability of two series that differ widely in their averages or which are measured in different units, we calculate the coefficients of dispersion, which being ratios are numbers independent of the units of measurement. The coefficients of dispersion (C.D.) based on different measures of dispersion are as follows: (a) C.D. based on range: (b) Based on quartile deviation: (c) Based on mean deviation: (d) Based on standard deviation: xmax − xmin xmax + xmin Q − Q1 C.D. = 3 Q3 + Q1 = C.D. = mean deviation average from which it is calculated S.D. σ = C.D. = Mean x

Coefficient of variation. It is the percentage variation in the mean, standard deviation being considered as the total variation in the mean.
C.V. =

σ

x

×100.

21.12 COEFFICIENT OF DISPERSION 1175 ________________________________________________________________________________________________________

ILLUSTRATIVE EXAMPLES

Example 1. Find the mean and standard deviation of the following:
Series 15–20 20–25 25–30 30–35 35–40 40–45 Frequency 2 5 8 11 15 20 Series 45–50 50–55 55–60 60–65 65–70 70–75 Frequency 20 17 16 13 11 5

Sol.
Mid-values x 17.5 22.5 27.5 32.5 37.5 42.5 47.5 52.5 57.5 62.5 67.5 72.5 f 2 5 8 11 15 20 20 17 16 13 11 5 N = 143 x = a + h⋅ Σ fu 5 = 47.5 + 5 × = 47.7 N 143
2 2

u=

x − 47.5 5 –6 –5 –4 –3 –2 –1 0 1 2 3 4 5

fu – 12 – 25 – 32 – 33 – 30 – 20 0 17 32 39 44 25 5

fu2 72 125 128 99 60 20 0 17 64 117 176 125 1003

1 1003 ⎛ 5 ⎞ ⎛ Σ fu ⎞ Σ fu 2 − ⎜ −⎜ σ x = hσ u = h ⎟ =5 ⎟ = 5 × 2.65 = 13.25. N 143 ⎝ 143 ⎠ ⎝ N ⎠

Example 2. Goals scored by two teams A and B in a soccer season were as follows:
No. of goals scored in a match 0 1 2 3 4 Find out which team is more consistent. No. of matches A B 27 17 9 9 8 6 5 5 4 3

2 N 40 2 2 dx = x – 2 –2 –1 0 1 2 fdx – 34 –9 0 5 6 –32 fd x2 68 9 0 5 12 94 σ= 1 94 ⎛ −32 ⎞ ⎛ Σ fd x ⎞ Σ fd x2 − ⎜ ⎟ = 40 − ⎜ 40 ⎟ = 1. If the two series are grouped together as one series of (n1 + n2) members.6 1.2 Since the coefficient of variation is less for team B.1176 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Sol.31 N ⎝ ⎠ ⎝ N ⎠ Coefficient of variation for team A = σ x × 100 = 1. of goals scored (x) 0 1 2 3 4 No.13 THEOREM σ The standard deviations of two series containing n1 and n2 members are σ1 and σ2 respectively. Coefficient of variation for team B = × 100 = 21. of matches (f) 27 9 8 5 4 N = 53 x =a+ Σ fd x −50 = 2+ = 2 − 0. of matches (f) 17 9 6 5 3 N = 40 x =a+ Σ fd x 32 = 2− = 2 − . being measured from their respective means x1 and x2 .06 Calculation of coefficient of variation for team B: No.3 × 100 = 108. team B is therefore more consistent. is given by .3 N ⎝ ⎠ ⎝ N ⎠ 1. of goals scored (x) 0 1 2 3 4 No.94 = 1. measured from its mean x . show that the standard deviation σ of this series.06 N 53 2 2 dx = x − 2 –2 –1 0 1 2 fdx – 54 –9 0 5 8 – 50 fd x2 108 9 0 1 56 138 σ= 1 138 ⎛ −50 ⎞ ⎛ Σ fd x ⎞ Σ fd x2 − ⎜ ⎟ = 53 − ⎜ 53 ⎟ = 1.31× 100 = 123.3 x 1.8 = 1. Calculation of coefficient of variation for team A: No.

If the whole group has 250 items with mean 15.6 and standard deviation 13. n1 + n2 (n1 + n2 ) 2 ( ∵ S2 = σ 2 ) Example. if a = x . d 2 = x2 − a If a is the mean of the two combined series.6 = n1 + n2 250 . then S2 = σ 2 n x +n x Also x= 1 1 2 2 n1 + n2 ∴ d1 = x1 − x = x1 − d 2 = x2 − x = x2 − ∴ n1d12 + n2 d 22 = = ∴ From (1). i..⎥ ⎢ n1 1 ⎣ ⎦ 2 n1 (σ 12 + d12 ) + n2 (σ 2 + d 22 ) = [∵ S2 = a 2 + d 2 where d = x − a ] n1 + n2 = 2 n1σ 12 + n2σ 2 n1d12 + n2 d 22 + n1 + n2 n1 + n2 . The first of the two samples has 100 items with mean 15 and standard deviation 3.21. σ 2 = n1 x1 + n2 x2 n2 ( x1 − x2 ) = n1 + n2 n1 + n2 n1 x1 + n2 x2 n1 ( x2 − x1 ) = n1 + n2 n1 + n2 2 n1n2 ( x1 − x2 ) 2 n2 n12 ( x2 − x1 ) 2 + (n1 + n2 ) 2 (n1 + n2 ) 2 n1n2 ( x1 − x2 ) 2 nn ⋅ (n2 + n1 ) = 1 2 ( x1 − x2 ) 2 2 n1 + n2 (n1 + n2 ) 2 n1σ 12 + n2σ 2 n1n2 + ( x1 − x2 ) 2 . find the standard deviation of the second group.44 n2 = 250 − 100 = 150 n x +n x 100(15) + 150( x2 ) x = 1 1 2 2 . σ = 13. x1 = 15. (1) Now d1 = x1 − a. σ 1 = 3 n = n1 + n2 = 250. + 2 n1 + n2 (n1 + n2 ) 2 Proof.44 .13 THEOREM 1177 ________________________________________________________________________________________________________ σ2 = 2 n1σ 12 + n2σ 2 n1n2 ( x1 − x2 ) 2 . Sol. we have 15.6. Here ∴ Using n1 = 100. we have S2 = = 1 n1 + n2 n1 + n2 ∑ 1 f ( x − a)2 = n1 + n2 ⎤ 1 ⎡ n1 f ( x − a)2 + ∑ f ( x − a)2 ⎥ ⎢∑ n1 + n2 ⎣ 1 n1 +1 ⎦ 2 n1S1 + n2S2 2 n1 + n2 ⎡ ⎤ 1 n1 2 ∵ S1 = ∑ f ( x − a) 2 etc. Let S1 and S2 be the mean square deviations of the two series respectively and S2 be 2 the mean square deviation of the two series taken together. .e. . Then if a is the assumed mean. x = 15.

The value of Bowley’s coefficient of skewness lies between –1 and +1 and that of Karl Pearson’s coefficient of skewness lies between –3 and +3.e.6 − 1500 = 2400 d1 = x1 − x = 15 − 15. Skewness indicates whether the curve is turned more to one side than to the other. Relative measures of skewness are called the coefficient of skewness.4 ∴ x2 = 16 The variance of the combined group σ 2 is given by the formula σ2 = or 2 n1σ 12 + n2σ 2 n1d12 + n2 d 22 + n1 + n2 n1 + n2 2 (n1 + n2 )σ 2 = n1 (σ 12 + d12 ) + n2 (σ 2 + d 22 ) 2 ∴ 250 ×13. then using M0 = 3Md – 2M.e. Skewness can be positive as well as negative. Bowley’s coefficient of skewness based on quartiles is defined as Sk = (Q3 − M d ) − (M d − Q1 ) Q3 + Q1 − 2M d = (Q3 − M d ) + (M d − Q1 ) Q3 − Q1 M − M0 Mean − Mode = σ Standard Deviation 3(M − M d ) Karl Pearson’s coefficient of skewness is defined as Sk = If the mode is ill-defined..14 SKEWNESS For a symmetrical distribution. 21.6 = −0.6 = 0. 21. they are pure numbers.15 MEASURES OF SKEWNESS Measures of skewness give us an idea about the extent of “lopsided-ness” in a series. .16) 2 or 150σ 2 = 250 ×13. Such measures should be (i) Pure numbers so as to be independent of the units in which the variable is measured. and median coincide and the median lies halfway between the two quartiles.36 − 150 × 0.36) + 150(σ 2 + 0. variates equidistant from the mean have equal frequencies. Hence σ 2 = 4. Thus M = M0 = Md and Q3 – M = M – Q1. we have Sk = σ . i.6 d 2 = x2 − x = 16 − 15. mode.16 = 3360 − 936 − 24 = 2400 2 ∴ σ 2 = 16. whether the curve has a longer tail on one side. The object of measuring skewness is to estimate the extent to which a distribution is distorted from a perfectly symmetrical distribution.1178 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ or 150 xx = 250 ×15. the mean. (ii) Zero when the distribution is symmetrical. Skewness means a lack of symmetry or lopsidedness in a frequency distribution. i. Skewness is positive if the longer tail of the distribution lies toward the right and negative if it lies toward the left. They are independent of the units of measurement and as such. in the case of such a distribution. Also.44 − 100 × 9. the frequencies are symmetrically distributed about the mean..55 = 100(9 + 0.

N 230 The greatest frequency 50 lies in the class 110–120.21.2 = = −0. 12 30 65 107 157 202 222 230 u= fu – 36 – 36 – 35 0 50 90 60 32 = 125 fu2 108 72 35 0 50 180 180 128 = 753 Σ fu 125 = 105 + 10 × = 105 + 5. of people (f) 12 18 35 42 50 45 20 8 N = 230 Mean M = a + h C.F.4 M − M 0 110. h = 10. of people 12 18 35 42 Wage bonuses (in $) No. l = 110. Hence this is the modal class.4 = Rs. f 2 = 45.2 = $116.3 ∴ Coefficient of dispersion = = = 0. Find the coefficient of dispersion and a measure of skewness from the following table giving the wage bonuses of 230 people: Wage bonuses (in $) 70–80 80–90 90–100 100–110 No. of people 110–120 50 120–130 45 130–140 20 140–150 8 x − 105 10 –3 –2 –1 0 1 2 3 4 Sol.4 − 116.4.2 100 − 42 − 45 13 2 2 1 753 ⎛ 125 ⎞ ⎛1 ⎞ Standard deviation σ = h Σ fu 2 − ⎜ Σ fu 2 ⎟ = 10 −⎜ ⎟ = $17.16 MOMENTS 1179 ________________________________________________________________________________________________________ Example.3 N 230 ⎝ 230 ⎠ ⎝N ⎠ σ 17. f m − f1 ∴ Mode M 0 = l + ×h 2 f m − f1 − f 2 = 110 + 50 − 42 83 ×10 = 110 + = 110 + 6. f m = 50. f1 = 42.16 MOMENTS The rth moment of a variable x about any point A is denoted by μr′ and is defined as μr′ = 1 Σ f ( x − A) r N where N=Σ f .33. Measure of skewness Sk = σ 17. 110. Mid-values (x) 75 85 95 105 115 125 135 145 No.3 21.16 M 110.

by definition. μ1 = 0. . N The results μ0 = 1.17 RELATION BETWEEN MOMENTS ABOUT THE MEAN IN TERMS OF MOMENTS ABOUT ANY POINT AND VICE VERSA By definition. . μr′ = 1 Σ f ( x − A) r N 1 = Σ fd r N where A is any point where d = x − A . ∴ or Now 1 Σ fd N 1 M = A + Σ fd = A + μ1′ N μ1′ = M − A μ1′ = . . 1 Σ f ( x − M) = 0 N | being the algebraic sum of the deviations from the mean 1 μ2 = Σ f ( x − M) 2 = σ 2 . + (−1) r ⋅ μ1′r ⎤ ⎣ ⎦ fd r − r C1μ1′ ⋅ 1 1 Σ fd r −1 + r C2 μ1′2 Σ fd r − 2 N N 1 1 − r C3 μ ′3 Σ fd r −3 + . μ1 = 21. . μ2 = σ 2 are of fundamental importance and should be committed to memory. 3. we get ′ ′ ′ μ2 = μ2 − 2 μ1′2 + μ0 μ1′2 = μ2 − μ1′2 ′ ′ ′ ′ ′ ′ μ3 = μ3 − 3μ2 μ1′ + 3μ23 − μ0 μ1′3 = μ3 − 3μ2 μ1′ + 2μ1′3 ′ ′ ′ ′ μ4 = μ4 − 4 μ3 μ1′ + 6μ2 μ1′2 − 4 μ1′μ1′3 + μ0 μ1′4 ′ ′ ′ = μ4 − 4 μ3 μ1′ + 6μ2 μ1′2 − 3μ1′4 ′ | ∵ μ0 = 1 . . . (i) Setting r = 1. setting r = 2. . . + (−1) r μ1′r | Using (i) In particular. . + (−1) r μ1′r ⋅ Σ f N N r r 2 r 3 = μr′ − C1μr′−1 + C2 μr′− 2 μ1′ − C3 μr′−3 μ1′ + . . 4.1180 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ The rth moment of a variable x about the mean M is denoted by μr and is defined as 1 μr = Σ f ( x − M) r N 1 1 1 ′ In particular μ0 = Σ f ( x − A)0 = Σ f = ⋅ N = 1 N N N μ0 = 1 Similarly. (ii) μr′ = 1 Σ N 1 = Σ N 1 = Σ N 1 = Σ N f ( x − M) r f ( x − A + A − M) r = 1 Σ f (d − μ1′) r N | Using (ii) f ⎡ d r − r C1d r −1μ1′ + r C2 d r − 2 μ1′2 − r C3 d r −3 μ1′3 + .

W. μ0 = 1. μ3 (corrected) = μ3 12 1 7 4 μ4 (corrected) = μ4 − h 2 μ2 + h where h is the width of class intervals. .19 SHEPPARD’S CORRECTIONS FOR MOMENTS In the case of class intervals we assume that the frequencies are concentrated at mid-points of class intervals. + μ1′r ⋅ Σ f N N N N 2 r r r = μ r + C1 μ r −1 μ1′ + C 2 μ r − 2 μ1′ + . 2 240 . 21. Sheppard gave the following formulae by which these errors may be corrected. x = A + hu h = A + hu . + μ1′r ) N 1 1 1 1 = Σ fd r + r C1 μ1′ ⋅ Σ fd r −1 + r C 2 μ1′2 Σ fd r − 2 + .e. . we get ′ μ4 = μ4 + 4μ3 μ1′ + 6μ2 μ1′2 + 4μ1μ1′3 + μ0 μ1′4 = μ4 + 4μ3 μ1′ + 6μ 2 μ1′2 + μ1′4 . some error is likely to creep into the calculation of moments. Since this assumption is not true in general. where bar denotes the mean of the respective variable = h(u − u ) 1 1 1 = Σ f ( x − A) r = Σ fh r u r = h r ⋅ Σ fu r N N N 1 1 1 = Σ f ( x − x ) r = Σ fh r (u − u ) r = h r ⋅ Σ f (u − u ) r N N N Hence the rth moment of the variable x is hr times the corresponding moment of the variable u. . . . 4 and noting that μ1 = 0. 1 μ2 (corrected) = μ2 − h 2 . + μ1′ ′ μ2 = μ2 + 2μ1μ1′ + μ0 μ1′2 = μ2 + μ1′2 ′ μ3 = μ3 + 3μ2 μ1′ + 3μ1μ1′2 + μ0 μ1′3 = μ3 + 3μ2 μ1′ + μ1′3 . (iii) | Using (ii ) | Using (iii ) In particular.21. .19 SHEPPARD’S CORRECTIONS FOR MOMENTS 1181 ________________________________________________________________________________________________________ Hence μ1 = 0 ′ μ 2 = μ 2 − μ1′2 ′ ′ ′ μ3 = μ3 − 3μ 2 μ1′ + 2 μ33 ′ ′ ′ μ 4 = μ 4 − 4 μ3 μ1′ + 6 μ 2 μ1′ − 3μ1′ 2 4 ′ ( μ1 = M − A) Conversely. .18 EFFECT OF A CHANGE OF ORIGIN AND SCALE ON MOMENTS Let ∴ ∴ u= x x−x μr′ Also μr x−A i. 3. setting r = 2. 21..F. . μ r = Now 1 1 Σ f ( x − M) r = Σ fd r where d = x − M N N 1 1 1 μ r′ = Σ f ( x − A) r = Σ f ( x − M + M − A) r = Σ f ( d + μ1′) r N N N 1 = Σ f ( d r + r C1d r −1 μ1′ + r C 2 d r − 2 μ1′2 + r C 3 d r −3 μ1′3 + .

β1 ( β 2 + 3) Base upon mom ed ments. 2(5β 2 − 6 β1 − 9) 21.22 KURTOSIS K Give two freq en quency distr ributions th have the same vari hat e iability as m measured by the y standard deviation. 21.20 CHARLIER’S CHECK C To check the accuracy in the calcula a ation of the first four m moments.1182 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ 21. y y trical but it m not be equally flat to may opped with t normal c the curve. then he he μ2 r +1 = 1 n ∑ fi ( xi − x )2r +1 . they may be relatively m t e more or less flat topped than the “n s d normal curve A e”. Curv that are flatter than the norma curve (see ves e n al e curve B in the figure are called platykurtic For such a e) d c.23 β1 AS A MEA ASURE OF SKEWNESS For a symmetric distributi cal ion. Curv that are neither flat nor sharply peaked are ves t y e called no ormal curves or mesokurtic curves ( s (see curve A in the fig gure). curve β 2 < 3 and hen γ 2 < 0. h nce 21. . frequency curve may be symmet The relat flatness of the top is called kurto and is m tive s osis measured by β 2 . nce Curv that ar more sh ves re harply peake than the ed e normal c curve (see curve C in the figure are called n e) d leptokurt For such a curve β 2 > 3 and hen γ 2 > 0. 3 μ2 1 β2 = μ4 . γ = + β1 . n Let x denote th mean of th variate x. γ = β2 − 3 2 μ2 2 These coefficie ents are ind dependent o units of measureme and the of ent erefore. N = Σ fi N i =1 . For suc a curve β 2 = 3 and h ch hence γ 2 = 0.21 PEARSON’S β AND γ C P S COEFFICIEN NTS Karl Pearson defined the f l following fo coefficie our ents based u upon the fir four mom rst ments about the mean: e β1 = μ32 . w often use the we e following identities known as Ch g k harlier check ks: Σ f ( x + 1) = Σ fx + Σ f = Σ fx + N Σ f ( x + 1) 2 = Σ fx 2 + 2Σ fx + N Σ f ( x + 1)3 = Σ fx3 + 3Σ fx 2 + 3Σ fx + N Σ f (x + 1) 4 = Σ fx 4 + 4Σ fx 3 + 6Σ fx 2 + 4Σ fx + N. are pure . tic. numbers. all the m moments of o order ab odd bout the mean vanish. the co oefficient of skewness is Sk = f s .

Let us first calculate moments about x = 4. μ4 = μ4 − 4μ3 μ1′ + 6μ2 μ1′2 − 3μ1′4 = 11 μ32 β1 = 3 = 0.23 β1 AS A MEASURE OF SKEWNESS 1183 ________________________________________________________________________________________________________ In a symmetrical distribution. ∴ f1 ( x1 − x ) 2 +1 + f n ( xn − x ) 2 r +1 = 0 [∵ x1 − x and xn − x are equal in magnitude but opposite in sign. 3 u2 Thus. again the N i =1 terms cancel in pairs and the middle term vanishes.e. Also f1 = f n ] Similarly f 2 ( x2 − x ) 2 r +1 + f n −1 ( xn −1 − x ) 2 r +1 = 0 and so on. In particular μ3 = 0 and hence β1 = μ32 μr′ = x f 1 1 Σ f ( x − 4) r = Σ fd r N N d=x–4 fd where d = x − 4 fd 2 fd 3 fd 4 0 1 2 3 4 5 6 7 8 1 8 28 56 70 56 28 8 1 N = 256 –4 –3 –2 –1 0 1 2 3 4 –4 – 24 – 56 – 56 0 56 56 24 4 0 16 72 112 56 0 56 112 72 16 512 – 64 – 216 – 224 – 56 0 56 224 216 64 0 256 648 448 56 0 56 448 648 256 2816 1 1 512 ′ Σ fd = 0. i. μ2 = μ2 − μ1′2 = 2 ′ ′ ′ ′ ′ μ3 = μ3 − 3μ2 μ1′ + 2μ1′3 = 0. Hence μ2 r +1 = 0 ∴ If n is even. μ2 β2 = μ4 11 = = 2. In n is odd. Example.75. Calculate the first four moments of the following distribution about the mean and hence find β1 and β 2 : x : 0 1 2 3 4 5 6 7 8 f : 1 8 28 56 70 56 28 8 1 Sol. μ4 = Σ fd 4 = = 11 N N 256 μ1′ = Moments about the mean are ′ μ1 = 0 (always ). β1 gives a measure of departure from symmetry.21. of skewness. since the middle term = x . the values of the variate equidistant from the mean have equal frequencies. 1 n ∑ fi ( xi − x )2r +1 cancel in pairs. μ2 = Σ fd 2 = =2 N N 256 1 1 2816 ′ ′ μ3 = Σ fd 3 = 0. 2 μ2 4 .. all the terms in = 0.

5–68. and standard deviation: Grades obtained : No. 54. 28. of students 5 7 10 16 11 Grades 50–60 60–70 70–80 80–90 90–100 No.5 52. 2. 40.5–52. 39. 49. 34.5 60.2. Compute the standard deviation for the following data relating to grades obtained by 15 students: 12. 2 . 39. of students : : 0–6 8 6–12 10 12–18 12 18–24 9 24–30 5 3. Calculate the mean and standard deviation for the following: Size of item Frequency : : 6 3 7 6 8 9 9 13 10 8 11 5 12 4 7.5 44.5 68. of workers 4 24 21 18 5 3 5 8 2 9.5 28. 39. 30. 23. The following table shows the grades obtained by 100 candidates in an examination. 5. of candidates : 1–10 3 11–20 16 21–30 26 31–40 31 41–50 16 51–60 8 8. Calculate the quartile deviation of the grades of 63 students in Physics given below: Grades 0–10 10–20 20–30 30–40 40–50 No. of students 7 3 2 2 0 2.5–44.5 36. Compute the mean deviation from the median of the following distribution: : : 0–10 5 10–20 10 20–30 20 30–40 5 40–50 10 4. median. and 6. 21. Find the mean deviation from the mean of the following distribution: Class Frequency Grades No.5 No.5–28.5 20. 27. (i) The mean of five items of an observation is 4 and the variance is 5. Calculate the mean. If three of the items are 1. 21. (ii) Show that the variance of the first n positive integers is 1 12 ( n − 1).1184 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ TEST YOUR KNOWLEDGE 1. 37.5 12. Calculate the mean and standard deviation for the following distribution: x: f: 56 3 63 6 70 14 77 16 84 13 91 6 98 2 6. then find the other two.5–60.5–12.5–20.5–36. Calculate the mean and standard deviation of the following frequency distribution: Weekly bonus wages in $ 4.5–76.

The scores of two golfers for 10 rounds each are: A: B: 58 84 59 56 60 92 54 65 65 86 66 78 52 44 75 54 69 78 52 68 Which may be regarded as the more consistent player? 15. A student obtained the mean and standard deviation of 100 observations as 40 and 5 respectively. The heights and weights of 10 people are given below.5 16.5 No.0 13.23 β1 AS A MEASURE OF SKEWNESS 1185 ________________________________________________________________________________________________________ 10. The following are the rushing yards of two high school football teams A and B in a series of games: 12 47 115 12 6 16 73 42 7 4 19 51 119 37 36 48 84 43 29 0 Which team has the better running game and which is more consistent? 17. of people 50 45 20 8 12. Find the standard deviation for the following data giving bonus wages of 230 people: Bonus wages (in $) 70–80 80–90 90–100 100–110 No. It was later discovered that he had wrongly copied down an observation as 50 instead of 40. The following statistics of neck circumferences are available based upon the measurements of a typical group of college students: Mid-value (inches) 12. has a larger bonus wage bill? (ii) In which firm. A or B. of students 4 19 30 63 66 Mid-value (inches) 15. standard deviation. A or B. An analysis of monthly bonus wages paid to the workers in two firms A and B belonging to the same industry gives the following results: Number of workers Average monthly wage Variance of distribution of bonus wages Firm A 500 $186 81 Firm B 600 $175 100 (i) Which firm. 14.5 13. Compute the quartile deviation and standard deviation for the following: x: f: 100–109 15 110–119 44 120–129 133 130–139 150 140–149 125 150–159 82 160–169 35 170–179 16 11. of people 12 18 35 42 Bonus wages (in $) 110–120 120–130 130–140 140–150 No. of students 29 18 1 1 Compute the mean. A collar manufacturer is considering the production of a new type of collar to attract young men.0 15. 13. and variance.5 No.5 14. Calculate the correct mean and standard deviation. In which characteristic are they more variable? Height in cm : Weight in kg : A: B: 170 75 172 74 168 75 177 76 179 77 171 73 173 76 178 75 173 74 179 75 16.21. is there greater variability in individual bonus wages? (iii) Calculate the variance of the distribution of bonus wages of all the workers in the firms A and B taken together. .0 14.0 16.

36 2.1186 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 18. Show that for a discrete distribution: (i) β 2 > 1 (ii) β 2 > β1 Answers 1.24 CORRELATION In a bivariate distribution. 23184 3. the mean is 10. 12. and – 40. i. 162 4. 23. .9 $31. 17. if the change in one variable affects a change in the other variable. 15. 12.9. For a distribution. if the increase (or decrease) in one results in a corresponding increase (or decrease) in the other. variance is 15. and 76. –64.3 9.. Find the coefficient of skewness for the following distribution: Class 0– 5 5–10 10–15 15–20 x : f : Variate Frequency Frequency 2 5 7 13 Class 20–25 25–30 30–35 35–40 Frequency 21 16 8 3 19. Correlation is said to be perfect if the deviation in one variable is followed by a corresponding proportional deviation in the other.e. 20.24. variance is 16.25 0. B 0. 13. 6. 0. 16. 18.87 (i) 4.9 (i) B (ii) B (iii) $180. 7.. $16. 11.49.9. 24. 20. γ 1 is +1 and β 2 is 4.32 75. 8. Find the first four moments about the origin. 16. the correlation is said to be inverse or negative. i. 6.10 Height 0.52 A. 9.. the correlation between income and expenditure is positive. 0.64 14.4 $17. 40. 18. Calculate the quartile coefficient of skewness for the following distribution: 1–5 3 6–10 4 11–15 68 16–20 30 21–25 10 26–30 6 31–35 2 20. 116. E. and 50. Find the moments about the mean.68. E. 12. 22. If the two variables deviate in opposite directions. 1. If the two variables deviate in the same direction. 22. 1544. and μ 3 = –86.g.6. 4. 0.. 10. 15. 16.26 ________________________________________________________________________________________________________ 21.26 A –1 10. The first four moments of a distribution about the value 5 of the variable are 2. The first three moments of a distribution about the value 2 of the variable are 1. 24. 9. 7 39. Also show that the first three moments about x = 0 are 3.35. the variables are said to be correlated.72. 2.e. 9 32. 5. 32. 121. 14. the correlation is said to be direct or positive. 19. Show that the mean is 3. 10. if the increase (or decrease) in one results in a corresponding decrease (or increase) in the other.61 10. the correlation between volume and the pressure of a perfect gas or the correlation between price and demand is negative. 23.g.53. Calculate the first four moments about the mean for the following data: : : 1 1 2 6 3 13 4 25 5 30 6 22 7 9 8 5 9 2 21.

b. The correlation coefficient is independent of change of origin and scale. . a poor correlation is expected. ∴ 1 1 Σ( xi − x )( yi − y ) = Σ( xi yi − xi y − yi x + x y ) n n 1 1 1 1 = Σxi yi − y ⋅ Σxi − x ⋅ Σyi + (nx y ) n n n n 1 1 = Σxi yi − y ⋅ x − x ⋅ y + x ⋅ y = Σxi yi − x ⋅ y n n 1 1 σ x2 = Σ( xi − x ) 2 = Σ( xi2 − 2 xi x + x 2 ) n n 1 1 1 1 1 = Σxi2 − 2 x ⋅ Σxi + nx 2 = Σxi2 − 2 x ⋅ x + x 2 = Σxi2 − x 2 n n n n n 1 2 σ y = Σyi2 − y 2 n 1 Σxi yi − x y n rxy = ⎛1 2 2 ⎞⎛ 1 2 2⎞ ⎜ Σxi − x ⎟ ⎜ Σyi − y ⎟ ⎝n ⎠⎝ n ⎠ . h k COMPUTATION OF THE CORRELATION COEFFICIENT 1 Σ( xi − x )( yi − y ) n We know that rxy = σ xσ y Now Similarly.26 KARL PEARSON’S COEFFICIENT OF CORRELATION (OR PRODUCT MOMENT CORRELATION COEFFICIENT) The correlation coefficient between two variables x and y. . Let ( xi . If the dots are very close to each other and the number of observations is not very large.27 COMPUTATION OF THE CORRELATION COEFFICIENT 1187 ________________________________________________________________________________________________________ 21. y ) or rxy is a numerical measure of the linear relationship between them and is defined as 1 1 Σ( xi − x )( y1 − y ) Σ( xi − x )( yi − y ) Σ( xi − x )( y1 − y ) n rxy = = =n σ xσ y 1 1 Σ( xi − x ) 2 Σ( yi − y ) 2 Σ( xi − x ) 2 ⋅ Σ( yi − y ) 2 n n Note. a fairly good correlation is expected. The diagram of dots so obtained is called a dot or scatter diagram. If the dots are widely scattered.27 x−a y −b . n be a bivariate distribution.v= where a.25 SCATTER OR DOT DIAGRAMS This is the simplest method of the diagrammatic representation of bivariate data. h. 3. 2. Let us define two new variables u and v as u= 21. yi ) i = 1. Let the values of the variables x and y be plotted along the x-axis and y-axis on a suitable scale.21. there corresponds a point or dot in the xy-plane. k are constants. usually denoted by r ( x. 21. Then corresponding to every ordered pair. . then rxy = ruv . .

v= then rxy = ruv = . Grades in Economics : 78 : 84 Grades in Statistics 2 36 51 3 98 91 4 25 60 5 75 68 6 82 62 7 90 86 8 62 58 9 65 53 10 39 47 Calculate the coefficient of correlation. h k ⎛1 2 2 ⎞⎛ 1 2 2⎞ ⎜ Σui − u ⎟ ⎜ Σvi − v ⎟ ⎝n ⎠⎝ n ⎠ ILLUSTRATIVE EXAMPLES Example 1. Ten students got the following percentage of grades in Principles of Economics and Statistics: : 1 Roll Nos. x 78 36 98 25 75 82 90 62 65 39 Total y 84 51 91 60 68 62 86 58 53 47 u = x – 65 13 – 29 33 – 40 10 17 25 –3 0 –26 0 u= v = y – 66 18 – 15 25 –6 2 –4 20 –8 – 13 – 19 0 u2 169 841 1089 1600 100 289 625 9 0 676 5398 v2 324 225 625 36 4 16 400 64 169 361 2224 uv 234 435 825 240 20 – 68 500 24 0 494 2734 1 1 Σui = 0. Sol. Find the coefficient of correlation for the following table: . = x: y: 10 18 14 12 18 24 22 6 26 30 30 36 Hence Example 2. Let the grades in the two subjects be denoted by x and y respectively.787. v = Σvi = 0 n n 1 1 Σui vi − u v (2734) n 10 ruv = = 1 1 ⎛1 2 2 ⎞⎛ 1 2 2⎞ (5398) ⋅ (2224) ⎜ Σui − u ⎟ ⎜ Σvi − v ⎟ 10 10 ⎝n ⎠⎝ n ⎠ 2734 = 0.787 5398 × 2224 rxy = ruv = 0.1188 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ If 1 Σui vi − u v x−a y −b n u= .

Let u= y 18 12 24 6 30 36 x − 22 y − 24 .6 1 ⎤ ⎡1 1⎤ ⎡1 ⎢ 6 (19) − 4 ⎥ ⎢ 6 (19) − 4 ⎥ ⎣ ⎦⎣ ⎦ Example 3. ΣXY = 508. ΣX 2 = 650. however. Y = ΣY = ×100 = 4 n 25 n 25 1 ΣXY − X Y n Corrected rxy = ⎛1 2 2 ⎞⎛ 1 2 2⎞ ⎜ ΣX − X ⎟ ⎜ ΣY − Y ⎟ ⎝n ⎠⎝ n ⎠ . 1 1 = (−3) = − 6 2 1 1 (12) − 6 4 = 0. ΣY = 100. ΣX = 125. 4 6 u –3 –2 –1 0 1 2 –3 v –1 –2 0 –3 1 2 –3 u2 9 4 1 0 1 4 19 v2 1 4 0 9 1 4 19 uv 3 4 0 0 1 4 12 x 10 14 18 22 26 30 Total 1 1 1 1 Σui = (−3) = − .27 COMPUTATION OF THE CORRELATION COEFFICIENT 1189 ________________________________________________________________________________________________________ Sol. v = Σvi n n 6 2 1 Σui vi − u v n ruv = = ⎛1 2 2 ⎞⎛ 1 2 2⎞ ⎜ Σui − u ⎟ ⎜ Σvi − v ⎟ ⎝n ⎠⎝ n ⎠ u= Hence rxy = ruv = 0.6. later discovered at the time of checking that two pairs had been copied incorrectly as X Y while the correct values were X Y 6 14 8 12 8 6 6 8 Obtain the correct value of the correlation coefficient. Sol.21. while calculating the correlation coefficient between two variables X and Y from 25 pairs of observations. It was. ΣY 2 = 460. obtained the following results: n = 25. Corrected Σ X = 125 − 6 − 8 + 8 + 6 = 125 Corrected Σ X = 100 − 14 − 6 + 12 + 8 = 100 ⎫ ⎪ ⎪ ⎪ 2 2 2 2 2 Corrected Σ X = 650 − 6 − 8 + 8 + 6 = 650 ⎬ ⎪ Corrected ΣY 2 = 460 − 142 − 62 + 122 + 82 = 436 ⎪ ⎪ Corrected Σ XY = 508 − 6 ×14 − 8 × 6 + 8 ×12 + 6 × 8 = 520 ⎭ (Subtract the incorrect values and add the corresponding correct values) X= 1 1 1 1 ΣX = ×125 = 5. A computer. v= .

The following table gives. according to age. ⎛ 1 ⎞⎛ 1 ⎞ ⎛ 36 ⎞ 5 6 3 (1) ⎜ ⎟ ⎜ × 650 − 25 ⎟ ⎜ × 436 − 16 ⎟ ⎝ 25 ⎠ ⎝ 25 ⎠ ⎝ 25 ⎠ Example 4. .28 CALCULATION OF THE COEFFICIENT OF CORRELATION FOR A BIVARIATE FREQUENCY DISTRIBUTION If the bivariate data on x and y is presented on a two-way correlation table and f is the frequency of a particular rectangle in the correlation table. then 1 Σ fxy − Σ fx Σ fy n rxy = 1 1 2⎤⎡ 2⎤ ⎡ 2 2 ⎢Σ fx − n ( Σ fx ) ⎥ ⎢ Σ fy − n ( Σ fy ) ⎥ ⎣ ⎦⎣ ⎦ Since the change of origin and scale do not affect the coefficient of correlation. If z = ax + by and r is the correlation coefficient between x and y. Sol. ∴ rxy = ruv where the new variables u. show that 2 σ z2 = a 2σ x2 + b 2σ y + 2abrσ xσ y . ⇒ z = ax + by z = ax + by . Example. v are properly chosen.1190 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 1 4 × 520 − 5 × 4 4 5 2 25 5 = = = × = = 0. zi = axi + byi zi − z = a ( xi − x ) + b( yi − y ) Now σ z2 = Σ( zi − z ) 2 = Σ[a( xi − x ) + b( yi − y )]2 1 1 n n 1 = Σ ⎡ a 2 ( xi − x ) 2 + b 2 ( yi − y ) 2 + 2ab( xi − x )( yi − y ) ⎤ ⎦ n ⎣ 1 1 1 = a 2 ⋅ Σ( xi − x ) 2 + b 2 ⋅ Σ( yi − y ) 2 + 2ab ⋅ Σ( xi − x )( yi − y ) n n n 1 Σ( xi − x )( yi − y ) = a 2σ 2 + b 2σ 2 + 2abrσ σ y ∵ r= n x y x σ xσ y 21.67. the frequency of grades obtained by 100 students in an intelligence test: Age (in years) Grades 10–20 20–30 30–40 40–50 50–60 60–70 Total 18 4 5 6 4 19 19 2 4 8 4 2 2 22 20 2 6 10 6 4 3 31 21 4 11 8 4 1 28 Total 8 19 35 22 10 6 100 Calculate the coefficient of correlation between age and intelligence.

29 RANK CORRELATION Sometimes we have to deal with problems in which data cannot be quantitatively measured but qualitative assessment is possible.21. in general. Let a group of n individuals be arranged in order of merit or proficiency in possession of two characteristics A and B. different. . . . i = 1. 2. Mid value 15 25 35 45 55 65 x y 10–20 20–30 30–40 40–50 50–60 60–70 f v fv fv2 fuv 18 4 5 6 4 19 2 4 8 4 2 2 22 –1 – 22 22 16 20 2 6 10 6 4 3 31 0 0 0 0 4 11 8 4 1 28 1 28 28 13 21 f 8 19 35 22 10 6 100 Totals u –3 –2 –1 fu 24 – 38 – 35 fu2 72 76 35 0 10 24 217 fuv 30 20 9 0 2 –2 59 19 2 – 38 76 56 0 0 1 10 2 12 Totals – 75 – 32 126 59 y − 45 . 643 2894 1 1 ⎡ ⎤⎡ ⎤ 2 2 × ⎢ 217 − 100 (−75) ⎥ ⎢126 − 100 (−32) ⎥ 4 25 ⎣ ⎦⎣ ⎦ 21.25. The Pearsonian coefficient of correlation between the ranks xi’s and yi’s is called the rank correlation coefficient between the characteristics A and B for that group of individuals. yi ).29 RANK CORRELATION 1191 ________________________________________________________________________________________________________ Sol. Let age and intelligence be denoted by x and y respectively. Thus an individual who is ranked at the top for the characteristic A may be ranked at the bottom for the characteristic B. it is not necessary that the most intelligent individual may be the most beautiful and vice versa. if A stands for intelligence and B for beauty. . n be the ranks of the n individuals in the group for the characteristics A and B respectively. Let ( xi . For example. The ranks in the two characteristics are. v = x − 20 10 Let us define two new variables u and v as u = 1 Σ fuv − Σ fu Σ fv n rxy = ruv = 1 1 ⎡ 2 2⎤⎡ 2 2⎤ ⎢Σ fu − n (Σ fu ) ⎥ ⎢ Σ fv − n (Σ fv) ⎥ ⎣ ⎦⎣ ⎦ 1 59 − (−75)(−32) 59 − 24 100 = = = 0. .

. Example. . . Assuming that no two individuals are bracketed or tied in either classification. . . Σd i = Σ ( xi − yi ) = Σxi − Σyi = 0 always. This is called Spearman’s Formula for Rank Correlation. i. 1 1 n(n + 1) n + 1 ∴ x = y = (1 + 2 + 3 + .. .e. . (1) Now xi’s and yi’s are merely the permutations of n numbers from 1 to n. (2) [Using (1)] ∴ From (2).1192 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Thus the rank correlation coefficient r= Σ( xi − x )( yi − y ) Σ( xi − x ) 2 Σ( yi − y ) 2 1 Σ( xi − x )( yi − y ) n = σ xσ y . + n 2 = = Σyi2 6 If di denotes the difference in ranks of the ith individual. then di = xi − yi = ( xi − x ) − ( yi − y ) 1 2 1 2 Σdi = Σ [ ( xi − x ) − ( yi − y ) ] n n 1 1 1 = Σ( xi − x ) 2 + Σ( yi − y ) 2 − 2 ⋅ Σ( xi − x )( yi − y ) n n n 2 2 = σ x + σ y − 2rσ xσ y But 2 σ x2 = Σxi2 − x 2 = Σyi2 − y 2 = σ y [∵ x = y ] . ( xi . 1 1 n n 1 2 ⎡1 ⎤ 2 2 2 Σd i = 2σ x − 2rσ x = 2(1 − r )σ x = 2(1 − r ) ⎢ Σxi2 − x 2 ⎥ n ⎣n ⎦ ⎡ 1 n(n + 1)(2n + 1) (n + 1) 2 ⎤ = 2(1 − r ) ⎢ ⋅ − ⎥ 6 4 ⎦ ⎣m 2 6Σdi2 ⎡ 4n + 2 − 3n − 3 ⎤ (1 − r )(n − 1) = (1 − r )(n + 1) ⎢ or 1 − r = ⎥= n(n 2 − 1) 6 6 ⎣ ⎦ Hence 6Σdi2 r = 1− . This serves as a check on calculations. + n) = ⋅ = n n 2 2 n(n + 1) Σxi = 1 + 2 + 3 + . . y y ) for i ≠ j. . . n(n 2 − 1) Note. The grades secured by recruits in the selection test (X) and in the proficiency test (Y) are given below: Serial No : : X : Y 1 10 30 2 15 42 3 12 45 4 17 46 5 13 33 6 16 34 7 24 40 8 14 35 9 22 39 Calculate the rank correlation coefficient. both x and y take all integral values from 1 to n. yi ) ≠ ( x j . . + n = = Σyi 2 n(n + 1)(2n + 1) Σxi2 = 12 + 22 + .

This adjustment factor is to be added for each repeated item.5 –1 1 40 48 10 9 1 1 55 50 8 8 0 0 64 70 6 2 4 16 Total 0 72 .5 –1 1 50 45 9 10 –1 1 64 81 6 1 5 25 80 60 1 6 –5 25 75 68 2. and 6th ranks if they were ranked 4+5+6 slightly differently. Obtain the rank correlation coefficient for the following data: X: Y: X Y Ranks in X (x) Ranks in Y ( y ) d=x–y d2 68 62 64 58 75 68 50 45 64 81 80 60 75 68 40 48 55 50 64 70 Sol. grades are given. Their common rank = 2 equal in fourth place. they would have assumed the 4th. the item with the largest size is ranked 1.30 2 6Σ d 2 6 × 72 = 1− = 1 − 0. Their common rank = = 5. next largest 2. If any two or more individuals have the same rank or the same value in the series of grades. 5th. first of all. they would have assumed the 6th and 7th ranks if they were 6+7 = 6.5 3. Here the grades are given. In each series. X Y Ranks in X (x) Ranks in Y ( y ) d=x–y 10 30 9 9 0 0 r = 1− REPEATED RANKS 15 42 5 3 2 4 12 45 8 2 6 36 17 46 3 1 2 4 13 33 7 8 –1 1 16 34 4 7 –3 9 24 40 1 4 –3 9 14 35 6 6 0 0 22 39 2 5 –3 9 Total 0 72 d ∴ 21. In such cases. Add m(m 2 − 1) to Σd 2 where m stands for the number of times an item is 12 repeated.30 REPEATED RANKS 1193 ________________________________________________________________________________________________________ Sol. Here.4 2 9 × 80 n(n = 1) Here n = 9. 68 62 4 5 –1 1 64 58 6 7 –1 1 75 68 2. 3 1 Adjustment. then the above formula fails and requires an adjustment. if two individuals are ranked equal at the sixth place. .21. 1 1 ⎧ ⎫ 6 ⎨Σd 2 + m(m 2 − 1) + m(m 2 − 1) + . so write down the ranks. and so on. Therefore. This common average rank is the average of the ranks that these individuals would have assumed if they were slightly different from each other.6 = 0.5 3. each individual is given an average rank.5. Thus. write down ranks. . ⎬ 12 12 ⎭ r = 1− ⎩ Thus 2 n(n − 1) Example. If three individuals are ranked ranked slightly differently.

the value 68 occurs twice. 21. the value 75 occurs twice. . A line of regression is the straight line that gives the best fit in the least square sense to the given frequency. ⎬ 12 12 ⎭ r = 1− ⎩ 2 n(n − 1) 1 1 1 ⎡ ⎤ 6 ⎢72 + {2(22 − 1)} + {3(32 − 1)} + {2(22 − 1)}⎥ 12 12 12 ⎦ r = 1− ⎣ 2 10(10 − 1) 6 × 75 6 = 1− = = 0. it is called a line of regression and the regression is said to be linear. Had these values been slightly different. Therefore. 3 Similarly. 3. The value 64 occurs three times.545. it is called the line of regression of y on x and it gives the best estimate of y for any given value of x. Therefore. the common rank given to them is = 2 2. . there exists an association or relationship between them. Had these values been slightly different..5. Regression measures the nature and extent of correlation. when the curve is a straight line. it is called the line of regression of x on y and it gives the best estimate of x for any given value of y. they 2+3 would have been given the ranks 2 and 3. 990 11 21. 2. m has the values 2. they would have been given the ranks 3 and 4. the common rank given to them is 3+ 4 = 3. it is natural to want to know the extent to which one variable varies in response to a given variation in the other variable. In the particular case. . If the line of regression is so chosen that the sum of squares of deviation parallel to the axis of x is minimized [See part (b) of the figure on the next page]. Therefore the common rank given to them is = 6.32 LINEAR REGRESSION If two variates x and y are correlated. This curve is called the curve of regression and the relationship is said to be expressed by means of curvilinear regression.e. and 7. 6. 1 1 ⎧ ⎫ 6 ⎨Σd 2 + m(m 2 − 1) + m(m 2 − 1) + . Had these values been slightly different.1194 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ In the X-series. in the Y-series. 2 Thus. one is interested to know the nature of the relationship between the two variables. If the line of regression is so chosen that the sum of squares of deviation parallel to the axis of y is minimized [See part (a) of the figure on the next page]. i.31 REGRESSION ∴ Regression is the estimation or prediction of unknown values of one variable from known values of another variable. then the scatter diagram will be more or less concentrated around a curve. they would have 5+6+7 been given the ranks 5.5. After establishing the fact of correlation between two variables.

. f of (x − x ) σx σ Sim milarly. They are m mutually perpen ndicular. the two lines of regress . .33 LIN NES OF REGR RESSION 1195 __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ 21. (5) 2 ∴ F From (5). an nd Σ( x − x ) 2 = σ x nσ xσ y n ⇒ . .nσ x σx σy Hen from (3) the line of regression o y on x is y − y = r nce. nrσ xσ y = a.21. the two lines of reg e. the lin of regress ne sion of x on y is x − x = r x ( y − y) σy rσ y b= rσ y σx rσ x is called th regression coefficient of y on x and is denoted by byx . . . ). . y ). (2) y = a + bx x y − y = b( x − x ) e Subtracting (2) from (1). (1) . . t gression becom y = y and x = x . If r = ± 1. he n d is called th regression coefficient of x on y an is denoted by bxy . he n nd d σy Note If r = 0.33 LINES OF REGRESSIO L R ON Let the equation of the line of regression of y on x b n n be y = a + bx Then . . (4) becom gin mes Shif Σ( x − x )( y − y ) = aΣ( x − x ) + bΣ( x − x ) 2 Sinc ce Σ(x − x )( y − y ) 1 2 = r ∴ Σ( x − x ) = 0. (3) uations are The normal equ Σy = n + bΣx na Σyx = aΣx + bΣx 2 .0 + b. . l sion will coinci ide. which a two straigh lines parallel to the me are ht l X.and Y-axes respectivel and passing through their m ly means y and x . we have . . (4) fting the orig to ( x .

Proof. if bxy > 1.1196 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 21.v= where a. and r have the same sign. (1) | Using (1) Since bxy ⋅ bxy = r 2 ≤ 1 (∵ − 1 ≤ r ≤ 1) ∴ bxy ≤ Similarly. σx σy G. the other must be less than 1. then 1 <1 byx 1 < 1. rσ y rσ x Proof. σx σy Let byx > 1. then byx < 1. b. which is true.M. The arithmetic mean of regression coefficients is greater than the correlation coefficient. Let . h. The two regression coefficients are byx = y and bxy = x . k Thus. and k are constants u= h k rσ kσ k ⎛ rσ ⎞ k byx = y = r ⋅ v = ⎜ v ⎟ = bvu hσ u h ⎝ σ u ⎠ h σx h buv . between them = rσ y σx × rσ x σy = r 2 = r = coefficient of correlation. Property II. . rσ rσ Proof. . Regression coefficients are independent of the origin but not of scale. . Similarly. byx and bxy are both independent of a and b but not of h and k. We have to prove that > r or >r 2 2 2 σ y + σ x2 > 2σ xσ y or (σ x − σ y ) 2 > 0. rσ y rσ x + byx + bxy σx σy Proof. x−a y=b Proof . Regression coefficient of y on x = bxy = r Regression coefficient of x on y = bxy = r σx σy σy σx Since σ x and σ y are both positive. bxy = Property V. If one of the regression coefficients is greater than 1. Property III. The coefficients of regression are and . bxy . byx .34 PROPERTIES OF REGRESSION Property I. or Property IV. The correlation coefficient and the two regression coefficients have the same sign. byx . The correlation coefficient is the geometric mean between the regression coefficients.

21.35 ANGLE BETWEEN TWO LINES OF REGRESSION 1197 ________________________________________________________________________________________________________

21.35

ANGLE BETWEEN TWO LINES OF REGRESSION

If θ is the acute angle between the two regression lines in the case of two variables x and y, show that

tan θ =

1 − r 2 σ xσ y ⋅ 2 where r, σ x , σ y have their usual meanings. 2 r σx +σ y

Explain the significance of the formula when r = 0 and r = ± 1. Proof. Equations of the lines of regression of y on x and x on y are y− y = Their slopes are m1 = rσ y

σx

( x − x ) and x − x =

rσ x

σy

( y − y)

rσ y

σx

and m2 =

σy . rσ x

σ y rσ y − rσ x σ x m2 − m1 =± tan θ = ± σ2 1 + m2 m1 1+ y σ x2 σ x2 1− r2 σ y 1 − r 2 σ xσ y =± ⋅ ⋅ 2 =± ⋅ 2 2 2 r σx σx +σ y r σx +σ y

Since r 2 ≤ 1 and σ x , σ y are positive. ∴ Positive sign gives the acute angle between the lines. 1 − r 2 σ xσ y Hence tan θ = ⋅ 2 2 r σx +σ y 2 ∴ The two lines of regression are perpendicular to each other. Hence the estimated value of y is the same for all values of x and vice versa when r = ± 1, tan θ = 0 so that, θ = 0 or π . Hence the lines of regression coincide and there is a perfect correlation between the two variates x and y. rσ x 1 1 1 Σxy − x y σ x n Σxy − x y n Σxy − x y =n ⋅ = = 2 1 2 σy σ xσ y σy σy Σy − y 2 n 1 rσ y n Σxy − x y = . 1 2 σx 2 Σx − x n when r = 0, θ =

π

Note.

Similarly,

1198 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________

ILLUSTRATIVE EXAMPLES

Example 1. Calculate the coefficient of correlation and obtain the least square regression line of y on x for the following data:

x: y:
Sol.

1 9

2 8

3 10

4 12

5 11

6 13

7 14

8 16

9 15

Also obtain an estimate of y that should correspond on the average to x = 6.2. x 1 2 3 4 5 6 7 8 9 Total y 9 8 10 12 11 13 14 16 15 u=x–5 –4 –3 –2 –1 0 1 2 3 4 0 u = y – 12 –3 –4 –2 0 –1 1 2 4 3 0 u2 16 9 4 1 0 1 4 9 16 60 v2 9 16 4 0 1 1 4 16 9 60 uv 12 12 4 0 0 1 4 12 12 57

1 1 Σuv − u v (57) − 0 n 9 = rxy = ruv = ⎛1 2 2 ⎞⎛ 1 2 2⎞ ⎡1 ⎤ ⎡1 ⎤ ⎜ Σu − u ⎟ ⎜ Σv − v ⎟ ⎢ 9 (60) − 0 ⎥ ⎢ 9 (60) − 0 ⎥ n n ⎝ ⎠⎝ ⎠ ⎣ ⎦⎣ ⎦ 19 = 0.95 20 1 1 rσ y rσ v n Σuv − u v 9 (57) − 0 19 = = = = = 0.95 1 2 1 σx σu 20 2 Σu − u (60) − 0 n 9 1 1 x = 5 + Σu = 5, y = 12 + Σv = 12 9 9 = rσ y

Also

Equation of the line of regression of y on x is y− y = or or

σx

(x − x )

y − 12 = 0.95( x − 5) y = 0.95 x + 7.25

When x = 6.2, the estimated value of y = 0.95 × 6.2 + 7.25 = 5.89 + 7.25 = 13.14.

21.35 ANGLE BETWEEN TWO LINES OF REGRESSION 1199 ________________________________________________________________________________________________________

Example 2. In a partially destroyed laboratory record of an analysis of a correlation data, only the following results are legible: Variance of x = 9 Regression equations: 8x – 10y + 66 = 0, 40x – 18y = 214. What were (a) the mean values of x and y, (b) the standard deviation of y, and (c) the coefficient of correlation between x and y. Sol. (i) Since both the lines of regression pass through the point ( x , y ) therefore, we have

8 x − 10 y + 66 = 0 40 x − 18 y − 214 = 0 Multiplying (1) by 5, Subtracting (3) from (2), ∴ From (1), Hence (ii ) Variance of ∴ 40 x − 50 y + 330 = 0 32 y − 544 = 0 ∴ 8 x − 170 + 66 = 0 or x = 13,
2 x =σx = 9

. . . (1) . . . (2) . . . (3) y = 17 8 x = 104 ∴ x = 13 y = 17

. . . (a) (given)

σx = 3
y = .8 x + 6.6 and x = .45 y + 5.35

The equations of the lines of regression can be written as rσ y

∴ The regression coefficient of y on x is
The regression coefficient of x on y is
rσ x

σx

= .8

. . . (4) . . . (5) . . . (b)

σy

= .45

Multiplying (4) and (5), r 2 = .8 × .45 = .36 ∴ r = 0.6 (Positive sign with square root is taken because regression coefficients are positive.) From (4), .8σ x .8 × 3 = = 4. 0.6 r
TEST YOUR KNOWLEDGE

σy =

. . . (c)

1. (a) Calculate the correlation coefficient for the following heights in inches of fathers (X) and their sons (Y ) . X: 65 66 67 67 68 69 70 72 Y: 67 68 65 68 72 72 69 71

(b) Find the correlation coefficient between x and y from the given data: x: y: x: y: 78 125 89 137 97 156 69 112 59 107 79 138 68 123 57 108

(c) Find the correlation coefficient from the following data: 92 86 89 88 87 91 86 77 83 68 77 85 71 52 63 82 53 37 50 57

If r = 0. 9. and z in the following order: Ranks by x : Ranks by y : Ranks by z : 1 3 6 6 5 4 5 8 9 10 4 8 3 7 1 2 10 2 4 2 3 9 1 10 7 6 5 8 9 7 Using the rank correlation method. Calculate the coefficient of correlation for the following ages of husbands and wives: Husbands’s age Wife’s age x: y: 23 18 2 27 20 2 2 28 22 28 27 29 21 30 29 31 27 33 29 35 28 36 29 3. 8. 6. what would be the value of the coefficient of correlation? . y. Establish the formula σ x − y = σ x + σ y − 2rσ xσ y where r is the correlation coefficient between x and y. A sample of 12 fathers and their sons gave the following data about their heights in inches: Father Son : : 65 68 63 66 67 68 64 65 68 69 62 66 70 68 66 65 68 71 67 67 69 68 71 70 Calculate the coefficient of rank correlation. 4. If the two regression coefficients are 0.1200 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 2. 7. (a) Calculate the coefficient of correlation for the following table: x y 10–20 20–30 30–40 40–50 50–60 60–70 16–18 2 3 3 2 18–20 1 2 4 2 1 1 20–22 1 3 5 3 2 2 22–24 2 6 4 2 1 (b) Find the correlation between x (grades in mathematics) and y (grades in Engineering Drawing) given in the following data: x y 0–30 30–60 60–90 Total 10–40 5 — — 5 40–70 20 28 32 80 70–100 — 2 13 15 Total 25 30 45 100 5.8 and 0. show that the two lines of regression are parallel to the axes. discuss which pair of judges has the nearest approach to common likings in music.2. Ten competitors in a musical test were ranked by the three judges x. Ten students got the following percentage of grades in chemistry and physics: Students Grades in chemistry Grades in physics : : : 1 78 84 2 36 51 3 98 91 4 25 60 5 75 68 6 82 62 7 90 86 8 62 58 9 65 63 10 39 47 Calculate the rank correlation coefficient.

the exhaustive cases are 6 × 6 = 62. 12. 7x – 16y + 9 = 0. . y = 1.87y and y = 11. 13. 12. Then. For example: (i) Tossing a coin is a trial and the turning up of heads or tails is an event. In a partially destroyed sheet of laboratory data. Find the mean values and the correlation coefficient between x and y. x: 1 2 3 4 5 6 7 8 9 10 y: 10 12 16 28 25 36 41 49 40 50 11.3x + 1. (a) Trial and event.84 0.74 (iii) –0. the experiment is called a trial and the possible outcomes are known as events or cases.79 (ii) 3. y = 7. (a) 0.603 (b) 0.82 0.5y + 0. 0. 5. Answers 1. the number of cases favorable to the appearance of a multiple of 3 are two. x and y . only the equations giving the two lines of regression of y on x and x on y are available and are respectively.1.69x + 4. x = −0. for any one of the six faces that may turn up.96 (e) 0.8. 13. ________________________________________________________________________________________________________ 21. for any of the 6 numbers from 1 to 6 on one die can be associated with any of the 6 numbers on the other die. The cases that entail the occurrence of an event are said to be favorable to the event. and 6. It is the total number of possible outcomes in which the specified event happens.21. there are 6 exhaustive cases. Calculate the coefficient of correlation. while the number of cases favorable to the appearance of an even number are three.1034. 4.6595 x = 4. (b) Exhaustive events. Find also the two regression lines.50x. (c) Favorable events or cases. viz. For example: (i) In tossing a coin. y = 4. (ii) In throwing a die.64 r = 0. Two random variables have the regression lines with equations 3x + 2y = 26 and 6x + y = 31. heads and tails.13 – 0.5 (b) r = 0. there are two exhaustive cases. (ii) mean of y’s.36 THEORY OF PROBABILITY 1201 ________________________________________________________________________________________________________ 10.7395. 7.28 (b) 0. In general. The total number of all possible outcomes in any trial is known as exhaustive events or exhaustive cases. Let an experiment be repeated under essentially the same conditions and let it result in any one of the several possible outcomes.9. y = 0. (iii) In throwing two dice.7291 (a) 0. (a) Find the correlation coefficient and the equations of regression lines for the following values of x and y: x: 1 2 3 4 5 y: 2 5 3 8 7 (b) Find the correlation coefficient between x and y for the given values.36 THEORY OF PROBABILITY Here we define and explain certain terms that are used frequently. x = 0..4517 x and z 0. the exhaustive cases are 6n. Find (i) mean of x’s.5 2. 6.64 – 0. 2. For example: (i) In throwing a die.722 (a) r = 0. viz.96. The two regression equations of the variables x and y are x = 19. r − 0. 10.4 (i) 15. 5y – 4x – 3 = 0. and (iii) the correlation coefficient between x and y. x = 0.2y – 0. (ii) Throwing a die is a trial and getting 1 or 2 or 3 or 4 or 5 or 6 is an event. 4. 3 and 6. in throwing n dice. 11.5172. 9.

then exhaustive number of cases = n + m..37 (a) MATHEMATICAL (OR CLASSICAL) DEFINITION OF PROBABILITY If a trial results in n exhaustive. 6 are mutually exclusive since any outcome rules out the possibility of getting any other.e. the events “heads” and “tails” are mutually exclusive. If P(E) = 1. (2.. q or P(E) = Unfavorable number of cases = n−m = 1− m 21. However. n→∞ n . any card may appear in the draw so that the 52 different cases are equally likely. (d) Mutually exclusive events. Note 2. Since the number of cases favorable to the occurrence of E is m and the exhaustive number of cases is n. rules out) the occurrence of all others. (e) Equally likely events. Exhaustive number of cases n Note 1. For example: If a card is drawn from a deck of well-shuffled cards and replaced before drawing the second card.e. 5). i. 2). the possibility of getting tails in the same trial is ruled out. If P(E) = 0. For example: (i) When a card is drawn from a well-shuffled deck.1202 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ (ii) In a throw of two dice.37 (b) STATISTICAL (OR EMPIRICAL) DEFINITION OF PROBABILITY If in n trials. 5. Note 3. n m P(E) = and P(E) = n+m n+m We say that the “odds in favor of E” are n : m and the “odds against E” are m : n.e.e. Otherwise they are said to be dependent. then E is an impossible event. (ii) In throwing a die. Two or more events are said to be independent if the occurrence or non-occurrence of any one does not depend (or is not affected) by the occurrence or non-occurrence of any other. p and q are non-negative and cannot exceed 1. the result of the second draw is independent of the first draw. then the second draw is dependent on the first draw.4). viz. if the first card drawn is not replaced. (5. all the six faces numbered. all six faces are equally likely to come up... then the probability of occurrence of E is given by p or P (E) = Favorable number of cases m = . the chance of its occurrence is 100%. the number of cases unfavorable to the occurrence of E are n – m. E is called a certain event. 1). If n cases are favorable to E and m cases are favorable to E (i.. Events are said to be equally likely if there is no reason to expect any one in preference to any other. (4. mutually exclusive and equally likely cases and m of them are favorable to the occurrence of an event E. 2. unfavorable to E).e. Note 4. i. i. 0 ≤ p ≤ 1. ( f ) Independent and dependent events. 1.. 0 ≤ q ≤ 1. therefore. since if the outcome is heads. For example: (i) In tossing a coin. 3. (ii) In throwing a die. 21. the number of cases favorable to getting a sum of 6 is 5. 4. (3. an event E occurs m times. then the probability of the occurrence of E is given by p = P(E) = Lt m . The probability that the event E will not happen is given by = 1− p Exhaustive number of cases n n Obviously. if no two or more than two of them can happen simultaneously in the same trial. (1. 3). Events are said to be mutually exclusive or incompatible if the occurrence of any one of them precludes (i.

2. (ii) there is one card of each suit. 18 ×17 ∴ Exhaustive number of cases = 18C2 = = 153 2 ×1 7×6 Out of 7 white balls. 153 51 Example 2. 2 ×1 ∴ Favorable number of cases = 21 Probability = 21 7 = . 13 ×12 ×11×10 Favorable number of cases = 13C4 = ∴ = 715. ∴ Required probability = 13 ×13 ×13 ×13 ×13 2197 = . 2 can be drawn in 7C2 = = 21 ways. Required probability = 29 C2 × 20 C2 551 = . Sol. Out of 18 balls. ∴ Favorable number of cases = 29C2 × 20C2. 50. and 5 black balls. 4 × 3 × 2 ×1 Required probability = 715 143 11 = = .21. 270725 20825 (iii) 2 spades out of 13 can be drawn in 13C2 ways. 50 C5 15134 . 2 hearts out of 13 can be drawn in 13C2 ways. Find the probability that (i) all are diamonds. 52 × 51× 50 × 49 ∴ Exhaustive number of cases = 52C4 = = 270725. 4 × 3 × 2 ×1 (i) There are 13 diamonds in the deck and 4 can be drawn out of them in 13C4 ways. If x3 = 30. Two balls are drawn at random. Exhaustive number of cases 50C5. 4 cards can be drawn from a deck of 52 cards in 52C4 ways. Find the probability that they will both be white.37 (b) STATISTICAL (OR EMPIRICAL) DEFINITION OF PROBABILITY 1203 ________________________________________________________________________________________________________ ILLUSTRATIVE EXAMPLES Example 1. and (iii) there are two spades and two hearts. 270725 54145 4165 (ii) There are 4 suits. 270725 20825 Example 3. then the two tickets with numbers x1 and x2 must come out of 29 tickets numbered 1 to 29 and this can be done in 29C2 ways. 3. What is the probability that x3 = 30? Sol. Sol. A bag contains 50 tickets numbered 1. A bag contains 7 white. The other two tickets with numbers x4 and x5 must come out of the 20 tickets number 31 to 50 and this can be done in 20C2 ways. each containing 13 cards. . of which five are drawn at random and arranged in ascending order of magnitude (x1 < x2 < x3 < x4 < x5). 6 red. 2 can be drawn in 18C2 ways. . Favorable number of cases = 13C2 × 13C2 = 78 × 78 ∴ 78 × 78 468 = Required probability = . Four cards are drawn from a deck of cards. . . Favorable number of cases = 13CI × 13C1 × 13C1 × 13C1 = 13 × 13 × 13 × 13. Total number of balls = 7 + 6 + 5 = 18.

are called sample points. if an event E consists of m sample points. called a certain event. the sample space. . we call it a finite sample space. called the probability of that event and is denoted by P(E). is called an event.40 PROBABILITY OF THE IMPOSSIBLE EVENT IS ZERO. an event made up of two or more sample events) is the sum of the probabilities of the simple events comprising the compound event. Thus. T}. (iii) The probability of a compound event (i.e. P ( φ ) = 0 Impossible event contains no sample point. the rolling of a die. then the probability of E is P(E) = 1 1 m + + . As such. Thus P(S) = 1. S itself is an event. Thus S = {H. we shall deal with finite sample spaces only. i. = Number of sample points in S [By Axiom (ii)] This closely agrees with the classical definition of probability.. T}. For example. Out of the several possible outcomes of a random experiment.. essentially under the same conditions. Thus 0 ≤ P(E) ≤ 1.38 RANDOM EXPERIMENT Occurrences that can be repeated a number of times. . (In this chapter. The elements of S. The two sample points are H and T. Finite Sample Space. if a coin is tossed and H and T denote “Heads” and “Tails” respectively.e. For example. then S = {H.) Event. + m times = n n n Number of sample points in E . one and only one can take place in a trial. Also. If the number of sample points in a sample space is finite. Sample Space. the sample space. Sample Point. then the sample space S contains n sample points and the probability associated with each sample point is 1 .. if a coin is tossed. 21. or the tossing of a coin are random experiments. 21. For example. and whose result cannot be predicted beforehand are known as random experiments. (ii) The sum of the probabilities of all simple (elementary) events constituting the sample space is 1. Since S ⊂ S. the null set is also an event. Every elementary event contains only one sample point. . Every subset of S. called an impossible event. then e is called an elementary event. n Now. The set of all these possible outcomes is called the sample space for the particular experiment and is denoted by S. If e ∈ S. the sample space S and the impossible event φ are mutually exclusive.1204 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 21.e. a sample point) is associated a real number between 0 and 1. . the possible outcomes are H (Heads) and T (Tails). φ ⊂ S.39 AXIOMS (i) With each event E (i. if there are n equally likely possible outcomes of a random experiment.

If A and B are a two even then any nts. ⇒ 21. e. i. i. TH HEN (i) P ∩ B) = P(A) – P(B P(A B) (ii) P( ≤ P(A) (B) Proof. c A 21. P( A ∩ B) = P(B) – P( ∩ B) F WO TS (A A ∩ B = {p : p ∈ B and p ∉ A} Now A ∩ B an A ∩ B ar disjoint se and w nd re ets ( A ∩ B) ∪ (A ∩ B) = B P[( A ∩ B) ∪ (A ∩ B)] = P A P(B) ⇒ P( A ∩ B) + P(A ∩ B) = P(B A B) ⇒ P( A ∩ B) = P(B – P(A ∩ B B) B).e. y then n 0 ≤ P( ≤ 1.43 IF B ⊂ A.45 AD DDITION THEO OREM OF PRO OBABILITIES (OR THEOREM OF TOTAL P M PROBABILITY) 1205 __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ ⇒ S ∪φ = S ⇒ P(S ∪ φ ) = P(S) P(φ ) = 0. P(A ∪ B) = P(A) + P(B) – P( ∩ B) (A P(A or B) = P(A) + P(B) – P(A and B).21. ⇒ P(S) + P(φ ) = P(S) ⇒ 21. 21.43 B ⊂ A ⇒ P(B) ≤ P( 3. By 21.. . ⇒ Note Similarly. When B ⊂ A. P(E) ≥ 0 (E) ∴ P(A ∩ B ) ≥ 0 ⇒ P(A) – P P(B) ≥ 0 [Using (1)] [ P(B) ≤ P(A). (1) Now if E is any event.44 P(A P ∩ B) ≤ P(A) AND P ∩ B) ≤ P(B) P(A Proof. B and A ∩ B are disjoint and their union is A. e d n ⇒ B ∪ (A ∩ B ) = A ⇒ P[B ∪ (A ∩ B ) = P(A) )] ∩ B ) = P(A) ⇒ P(B) + P(A ⇒ P(A ∩ B ) = P(A – P(B) A) . w. . ∴ P(A ∪ A ) = P(S S) ⇒ P(A) + P( A ) = 1 Hence P( A ) = 1 – P(A A).e.41 P PROBABILIT OF THE COMPLEMENTARY EV TY VENT A OF A IS GIVEN BY F P( P A ) = 1 – P(A) P A a A are dis and sjoint events Also A ∪ A = S s.. A .45 A ADDITION THEOREM O PROBAB OF BILITIES (OR THEOREM OF TOTA R M AL PROBABILIT P TY) Stat tement. (A) ce Sinc (A ∩ B) ⊂ A and (A ∩ B) ⊂ B ∴ P(A ∩ B) ≤ P(A) and P(A ∩ B) ≤ P(B). it can be proved that P(A ∩ B ) = P(A) – P(A ∩ B).42 FOR ANY TW EVENT A AND B. ) 21.

Proof. A and A ∩ B are dis sjoint sets an their unio is A ∪ B.. so tha P(A ∩ B) = P φ ) = 0. ..47 IF A1...46 IF A. . . + An) = P(A1) + P 2) + . . or P(A + B + C) = P(A) + P 21.. Using the above Arti 21. for mutu e ) n ually disjoint events A and B. 21. at P( P(A ∪ B) = P(A) + P(B). . Thus.. then A ∩ B = φ .. An ARE n MUTUALLY EXCLUSIVE EVENTS THEN TH F Y S. (B) Note 1. a so on. . A2. ∪ An) = P(A1 + A2 + . B. ⎪ mn ⎪ bability of occurrence of event A n = P(A n ) = o f Prob N ⎪ ⎭ . P(A ∪ B) is also written as P(A + B). . m2 are favor m1 ⎫ Prob bability of occurrence of event A1 = P(A1 ) = o f N ⎪ ⎪ m2 ⎪ Prob bability of occurrence of event A 2 = P(A 2 ) = o f ⎪ . Let N be the total nu e umber of mu utually exclu usive. + P(An) P(A Proof. S 21. (1) N ⎬ ⎪ . ∴ Note 2. .45 fo two events we have A ) B) P(A ∪ B ∪ C) = P[(A ∪ B ∪ C] = P(A ∪ B + P(C) – P B) P[(A ∪ B) ∩ C] = [P(A) + P(B) – P(A ∩ B)] + P(C – P[(A ∩ C) ∪ (B ∩ C)] C) [By the distributive law] e e = P(A) + P P(B) + P(C) – P(A ∩ B) – [P(A ∩ C C)] + P(B ∩ C) – P{(A ∩ C) ∩ (B ∩ C)} [By Art....45] = P(A) + P P(B) + P(C) – P(A ∩ B) – P(A ∩ C) – P(B ∩ C) ) ) + P(A ∩ B ∩ C) [∵ (A ∩ C) ∩ (B ∩ C = A ∩ B ∩ C] C) = P(A) + P P(B) + P(C) – P(A ∩ B) – P(B ∩ C) – P(C ∩ A) ) + P(A ∩ B ∩ C) [∵ A ∩ C = C ∩ A] ) P(B) + P(C) – P(AB) – P P(BC) – P(CA) + P(ABC C). . . and of which m1 are favorable to A1.. P(A ∩ B) is also written as P(AB w B). AND C ARE AN THREE E D NY EVENTS. P(A + B) = P(A) + P( B (B). . exhaus stive and equ ually likely cases rable to A2.. TH HEN P(A ∪ B ∪ C) = P( + P(B) + P(C) – P(A ∩ B) – P(B ∩ C) – P( ∩ A) + P ∩ B ∩ C (A) A (C P(A C) or ) P(C) – P(AB – P(BC) – P(CA) + P B) P(ABC) P(A + B + C) = P(A) + P(B) + P icle or s..1206 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ Proof. nd on ⇒ A ∪ B = A ∪ ( A ∩ B) ⇒ P(A ∪ B) = P[A ∪ ( A ∩ B)] = P(A) + P(A ∩ B) ) A [P( B)] = P(A) + [ A ∩ B) + P(A ∩ B) – P(A ∩ B = P(A) + P A ∩ B) ∪ (A ∩ B)] – P[(A ∩ B)] P[( [∴ A ∩ B and A ∩ B are d disjoint] = P(A) + P P(B) – P(A ∩ B) [∵ ( A ∩ B) ∪ ( ∩ B) = B] (A P(A ∪ B) = P(A) + P( – P(A ∩ B). HE PROBABILIT OF THE OCCURREN P TY NCE OF ON OF THEM IS NE M P(A P 1 ∪ A2 ∪ ... . If A and B are two mutua disjoint eve e ally ents.

. Assuming that a dead heat is impossible. 1 : 4.. . + mn . the number of cases favorable to the event A1 or A2 or . . .48 CONDITIONAL PROBABILITY The probability of the occurrence of an event E1 when another event E2 is known to have already happened is called Conditional Probability and is denoted by P(E1/E2). .21. p4 be the probabilities of the horses A. C. . 1 1 = 1+ 3 4 1 1 1 p2 = . + P(A n ) = ILLUSTRATIVE EXAMPLES | Using (1) Example 1. .+ n N N N N = P(A1 ) + P(A 2 ) + . An event E1 is said to be independent of an event E2 if P(E1/E2) = P(E1) i. B. . . 1 : 5. Sol. p3 = . p2. the events are mutually exclusive. ∴ Probability of occurrence of one of the events A1.. P(AB) = 52 52 52 13 4 1 16 4 + − = = . A card is drawn from a well-shuffled deck of playing cards. p4 = . . An is P(A1 + A2 + . Let and A = the event of drawing a spade B = the event of drawing an ace AB = the event of drawing the ace of spades 13 4 1 P(A) = . What is the probability that it is either a spade or an ace? Sol. ∴ 21. . In a given race. then p = p1 + p2 + p3 + p4 = Example 2. . or An is m1 + m2 + . Mutually Independent Events. the odds in favor of four horses A. . respectively. . + An) m1 + m2 + . Odds in favor of A are 1 : 3 ∴ p1 = Similarly. Let p1.48 CONDITIONAL PROBABILITY 1207 ________________________________________________________________________________________________________ The events being mutually exclusive and equally likely. P(B) = . Since a dead heat (in which all the four horses cover the same distance in the same time) is not possible. 5 6 7 1 1 1 1 319 . 1 : 6 respectively. find the chance that a particular horse wins the race. D winning. A2. + mn m1 m2 m = + +. C. P(A + B) = P(A) + P(B) − P(AB) = 52 52 52 52 13 A and B are not mutually exclusive. p3. + + + = 4 5 6 7 420 If p is the chance that one of them wins. if the probability of the occurrence of E1 is independent of the occurrence of E2. B. ..e. D are 1 : 3.

m ∴ Conditional probability of B. An are n independent events. . . then Cor. (2) m Now. . If A1. mutually exclusive and equally likely outcomes. Note. 1. . (1 − pn ). for two events A and B. P(A ∩ B) = P(A) × P(B/A) where P(B/A) represents the conditional probability of the occurrence of B when the event A has already happened.e. P(A ∩ B) is also written as P(AB). . the probability of all of these failing is (1 − p1 )(1 − p2 ) . 2. 1 − pn and. Cor. If p is the chance that an event will occur in one trial then the chance that it will occur in a succession of r trials is p ⋅ p . Cor. A n ) = P(A1 ) × P(A 2 ) × . therefore. A2. . . Thus P(AB) = P(A) × P(B/A). m of them being favorable to the occurrence of the event A.1208 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 21. . p ⋅ (r times) = p r . . . then P(B/A) = P(B) [∵ B ∩ A = A ∩ B] . 4. .49 MULTIPLICATIVE LAW OF PROBABILITY (OR THE THEOREM OF COMPOUND PROBABILITY) The probability of the simultaneous occurrence of two events is equal to the probability of one of the events multiplied by the conditional probability of the other. given that A has happened = P(B/A) = 1 . . × P(A n ). . mutually exclusive and equally likely outcomes. p2 . Generalization. . Proof. Interchanging A and B P(BA) = P(B) × P(A/E) or P(AB) = P(B) × P(A/E) Cor. (1) n Out of m outcomes favorable to the occurrence of A. pn are the probabilities that certain events occur. . out of n exhaustive. P(AB) = P(A) × P(B). . . .. If p1 . . . P(A1A 2 . ∴ Probability of simultaneous occurrence of A and B m m m m m = P(A ∩ B) = 1 = 1 × = × 1 n m n n m = P(A) × P(B/A) [Using (1) and (2)] Hence P(A ∩ B) = P(A) × P(B/A). Hence the chance in which at least one of these events must occur is 1 − (1 − p1 )(1 − p2 ) . 3. m1 are favorable to the occurrence of A and B. m ∴ Probability of the occurrence of the event A = P(A) = . i. . . . then the probabilities of their non-occurrence are 1 − p1 . . 1 − p2 . let m1 be favorable to the occurrence of the event B. If A and B are independent events. (1 − pn ).. . . . Suppose a trial results in n exhaustive.

A can hit a target 4 times in 5 shots.49 MULTIPLICATIVE LAW OF PROBABILITY (OR THEOREM OF COMPOUND PROBABILITY) 1209 ________________________________________________________________________________________________________ ILLUSTRATIVE EXAMPLES Example 1. 1− = . C are 5 2 4 3 3 4 1− = . . C are . . 4 to 3. The probabilities p1 . respectively. What is the probability that the problem will be solved? 2 3 4 1 1 1 Sol. a majority will be favorable? Sol. B.21. 7 7 7 ∴ The probabilities that the book is unfavorably reviewed by A.. . . (i) If A. They fire a volley. p3 of the book being 5 4 3 favorably reviewed by A. B. C. C not solving the problem are 1 − . 7 7 7 7 7 7 A majority will be favorable if the reviews of at least two are favorable. B. Let the three critics be A. the probability is 5 4 4 80 | p1 p2 (1 − p3 ) × × = 7 7 7 343 (iii) If A. . C all review favorably. C review favorably and B reviews unfavorably. B. B review favorably and C reviews unfavorably. and 3 to 4 respectively. 1 − . 4 4 Example 2. B can hit it 3 times in 4 shots. 2 3 4 1 1 1 1 2 3 The probabilities of A. the probability is 2 4 3 24 | (1 − p1 ) p2 p3 × × = 7 7 7 343 Hence the probability that a majority will be favorable is 60 80 45 24 209 + + + = . The probabilities of A. C whose chances of 1 1 1 solving it are . 2 3 4 2 3 4 1 2 3 1 ∴ The probability that the problem is not solved by any of them = × × = . 2 3 4 4 1 3 Hence the probability that the problem is solved by at least one of them = 1 − = . 1− = . B. 343 343 343 343 343 Example 3. Probability of A’s hitting the target = 5 3 = Probability of B’s hitting the target 4 . C review favorably and A reviews unfavorably. the probability is 5 4 3 60 × × = | p1 p2 p3 7 7 7 343 (ii) If A. respectively. the probability is 5 3 3 45 | p1 (1 − p2 ) p3 × × = 7 7 7 343 (iv) If B. B. of the three reviews. . C can hit it twice in 3 shots. The odds that a book will be favorably reviewed by three independent critics are 5 to 2. A problem in mechanics is given to three students A. 1 − i. What is the probability that. C solving the problem are .e. . What is the probability that at least two shots hit? 4 Sol. p2 . B.

C all hit the target. throws. he should throw a one in the first or third or fifth. the probability of which is 4 ⎛ 3⎞ 2 4 1 2 8 × ⎜1 − ⎟ × = × × = . 6 6 6 6 6 6 6 6 6 6 6 6 6 ⎝6⎠ 6 ⎝6⎠ 6 2 3 . he should throw a one in the second or fourth or sixth. A having the first throw. ⋅ . B hit the target and C misses it. . the probability of which is 4 3 ⎛ 2 ⎞ 4 3 1 12 × × ⎜1 − ⎟ = × × = . The chance of throwing a one with a single die = 6 1 5 The chance of not throwing a one with a single die = 1 − = . . . A can draw two tickets (out of 3 + 5 = 8) in 8C3 = 28 ways. 60 60 60 60 60 6 Example 4. ⎝ 5 ⎠ 4 3 5 4 3 60 Since these are mutually exclusive events. B. Sol. ⋅ ⋅ ⋅ . . 5 4 ⎝ 3 ⎠ 5 4 3 60 (iii) A. The person who first throws a one wins. A has 2 shares in a lottery in which there are 3 prizes and 5 blanks. . . . third. . B has 3 shares in a lottery in which there are 4 prizes and 6 blanks. ∴ B can win a prize in 120 – 20 = 100 ways. the probability of which is ⎛ 4⎞ 3 2 1 3 2 6 ⎜1 − ⎟ × × = × × = . What are their respective chances of winning? 1 Sol. 5 4 3 60 (ii) A. ⎜ ⎟ ⋅ . . C hit the target and B misses it. A and B throw alternately with a single die. C hit the target and A misses it. . 6 6 If A is to win. the required probability is = 24 12 8 6 50 5 + + + = = .. 120 6 9 5 : = 27 : 35. . . ⎜ ⎟ ⋅ . The chances that a one is thrown in the first. A will get the blanks in 5C2 = 10 ways. ⋅ ⋅ . . ∴ A’s chance : B’s chance = 14 6 Example 5. Show that A’s chance of success is to B’s as 27 : 35. throws are 1 5 1 5 5 1 5 5 5 1 1 5 1 ⎛5⎞ 1 ⎛5⎞ 1 . or . . 5 ⎝ 4 ⎠ 3 5 4 3 60 (iv) B. ⋅ . If B is to win. throws. we may have (i) A. B will get all blanks in 6C3 = 20 ways. . the probability of which is 4 3 2 24 × × = . ∴ A can win a prize in 28 – 10 = 18 ways 18 9 Hence A’s chance of success = = 28 14 B can draw 3 tickets in 10C3 = 120 ways. . 3 For at least two hits.1210 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Probability of C’s hitting the target = 2 . 100 5 Hence B’s chance of success = = . second.

11 11 Example 6. Show that the probability that exactly n cards are dealt before the first ace appears is 4(51 − n)(50 − n)(49 − n) . P(B) = 13 2 = = C2 13 × 12 26 C2 13 × 12 26 P(C) = 10 C1 × 3 C1 10 × 3 10 = = 13 13 × 12 26 C2 2 ×1 . . C respectively. Consider the event A n cards can be drawn out of 52 cards in 52Cn ways. Exhaustive cases = 52–nC1 = 52 – n. Cards are dealt one by one from a well-shuffled deck until an ace appears. The two balls drawn from the first urn may be (i) both white (ii) both black (iii) one white and one black. . ⇒ Exhaustive cases = 52Cn n non-ace cards can be drawn out of 52 cards in 48Cn ways. B. Probability = P(A) ⋅ P(B/A) = (52 − n)(51 − n)(50 − n)(49 − n) 4 4(51 − n)(50 − n)(49 − n) × = . Let A be the event of drawing n non-ace cards and B. An urn contains 10 white and 3 black balls. = 6 ⎝6⎠ 6 ⎝6⎠ 6 2 4 1 6 6 = 2 ⎛ 5 ⎞ 11 1− ⎜ ⎟ ⎝6⎠ Sum of an infinite Geometric a Progression = 1− r B’s chance = 1 − 6 5 = . 52 ⋅ 51⋅ 50 ⋅ 49 Sol. ⇒ Favorable cases = 48Cn 48! (52 − n)!(n)! × ∴ P(A) = 48 Cn / 52 Cn = (48 − n)!n ! 52! 48! ⋅ (52 − n)(51 − n)(50 − n)(49 − n)(48 − n)! (52 − n)(51 − n)(50 − n)(49 − n) = = . Favorable cases = 4C1 = 4 4 ∴ P(B/A) = 52 − n Reqd.21.49 MULTIPLICATIVE LAW OF PROBABILITY (OR THEOREM OF COMPOUND PROBABILITY) 1211 ________________________________________________________________________________________________________ 1 ⎛5⎞ 1 ⎛5⎞ 1 ∴ A’s chance = + ⎜ ⎟ ⋅ + ⎜ ⎟ ⋅ + . 52 ⋅ 51⋅ 50 ⋅ 49 52 − n 52 ⋅ 51⋅ 50 ⋅ 49 Example 7. 10 3 C 10 × 9 15 C 3× 2 1 P(A) = 13 2 = = . Let these events be denoted by A. Two balls are drawn from the first urn and put into the second urn and then a ball is drawn from the latter. (48 − n)! ⋅ 52 ⋅ 51 ⋅ 50 ⋅ 49 ⋅ (48)! 52 ⋅ 51 ⋅ 50 ⋅ 49 Consider the event B n cards have already been drawn in the first n draws. while another urn contains 3 white and 5 black balls. What is the probability that it is a white ball? Sol. the event of drawing an ace in the (n + l)th draw.

P(W/C) = 10 10 10 ∴ Reqd. They fire a volley. 30. and 4 children. . and . 1 1 1 1 1 11. 2. 4% read both B and C. What is the probability that 3 will be red and 3 will be black? 6. and 2% read all three. 2. Show that 5 . Six cards are drawn at random from a deck of 52 cards. marked. Four people are chosen at random from a group containing 3 men. . 5% read both A and C. four tickets are drawn. probability = P(A) ⋅ P(W/A) + P(B) ⋅ P(W/B) + P(C) ⋅ P(W/C) 15 5 1 3 10 4 75 + 3 + 40 118 59 = ⋅ + ⋅ + ⋅ = = = . . 1. Find the odds against two specified individuals sitting next to each other. 4 are boys and the rest are girls. What is the chance that the latter then contains 2 red and 6 black balls? 8. 1 girl and 3 boys. 5 3 4 Now P(W/A) = . One child is selected at random from each group. Find the probability that a student selected will be a girl. Their chances of solving it are . 16% read B. and C hits it 3 times in 4 shots. respectively. 9. C are published in a city and a survey of readers indicates the following: 20% read A. . What is the probability that at least two shots hit the target? 13. 3 girls and 1 boy. Three newspapers A. An integer is chosen at random from the first two hundred positive integers. A problem in statistics is given to five students. 3. B hits it 4 times in 5 shots. Three groups of children contain. 8% read both A and B. 3. What is the chance that a (i) non-leap year (ii) leap year should have fifty-three Sundays? 3. . the second urn may contain (i) 5 white and 5 black balls (ii) 3 white and 7 black balls (iii) 4 white and 6 black balls. 1 girl and 2 boys is 32 14. three are drawn at random. Eight of them are placed in another urn. For a person chosen at random. B. 2. 14% read C. . A five-figured number is formed by the digits 0. What is the probability that the integer chosen is divisible by 6 or 8? 5. the chance that exactly two of them will be children is 21 . From a set of raffle tickets numbered 1 to 100. 4 (without repetition). A can hit a target 5 times in 6 shots. A party of n people sit at a round table. What are the odds against his winning the bet? 4.1212 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ When two balls are transferred from the first urn to the second urn. what is the chance that those marked 1 and 2 are among them? (b) An urn contains 5 red and 10 black balls. 2 women. (a) If from a lottery of 30 tickets. 2 3 4 4 5 What is the probability that the problem will be solved? 12. Show that the chance that the three selected consist of 13 . . (ii). find the probability that he reads none of the papers. 10. In a class of 10 students. and (iii). P(W/B) = . 2 girls and 2 boys. 26 10 26 10 26 10 260 260 130 TEST YOUR KNOWLEDGE 1. What is the probability that all are odd numbered? 7. Find the probability that the number formed is divisible by 4. 1. A card is drawn from an ordinary deck and a gambler bets that it is a spade or an ace. Let W denote the event of drawing a white ball from the second urn in the three cases (i).

19. A has 3 shares in a lottery where there are 3 prizes and 6 blanks. 16. (ii) two belong to the same class and the third to the different class. Five workers in a company of twenty are graduates. 23.49 MULTIPLICATIVE LAW OF PROBABILITY (OR THEOREM OF COMPOUND PROBABILITY) 1213 ________________________________________________________________________________________________________ 15. A ball is transferred from the box A to the box B. what is the probability that (ii) at least one is a graduate? (i) they are all graduates? 26.28.3. P(A ∩ C) = 0. and (iii) none of them will be selected? 29.8. 10% of these men and 20% of these women smoke ABC Cigarettes. For two events A and B.48. find their respective chances of winning. in order. 27. The probability of the husband’s selection is 1 and that of the wife’s selection is 1 . A speaks the truth in 60% of cases and B in 70% of cases. Two dice are tossed once.6 (i) Find p so that A and B are independent events. P(B) = p and P(A ∪ B) = 0. A committee consists of 9 students.4. P(A ∩ B) = 0. Three students are to be removed at random. P(C) = 0.75.08. If A begins. Of the cigarette-smoking population. A. Three balls are drawn at random from the bag. P(A ∩ B ∩ C) = 0. A wins if he throws 6 before B throws 7 and B wins if he throws 7 before A throws 6. and C. What is the chance that (i) the three students belong to different classes. If A. What is the probability of drawing an ace in a single draw from the remaining 50 cards? (b) A box A contains 2 white and 4 black balls. C are events such that P(A) = 0. three are in their 2nd year. (ii) two balls are of the same color. 18. A bag contains 10 balls. three are blue. . If A starts. What is the probability that (i) the three balls are of different colors. A and B throw alternately with a pair of ordinary dice. and (iii) the three belong to the same class? 25. Another box B contains 5 white and 7 black balls. The first one to throw a head wins. B. Find the probability that it is white. 70% are men and 30% are women. 17. What is the probability that 7 5 (i) both of them will be selected. 20. If 3 workers are picked out of 20 at random. A husband and wife appear in an interview for two vacancies in the same position. P(B) = 0. and four are in their 3rd year. toss a coin. and five are black. (ii) only one of them will be selected. Find the chance of throwing 5 or 6 at least once in four throws of a die.4.09 If P(A ∪ B ∪ C) ≥ 0. Find the probability of getting an even number on the first throw or a total of 8. (iii) the balls are all of the same color. two of which are red. (Huygen’s Problem) 22. then a ball is drawn from box B. (ii) For what value of p are A and B mutually exclusive? 28. In what percentages of cases are they likely to contradict each other in stating the same fact? 21. B has one share in another. Find the probability that at least one of these people will be alive 30 years from now. then show that 0. It is 8 : 5 against a person who is 40 years old living until they are 70 and 4 : 3 against a person now 50 living until they are 80. Show that A has a better chance of winning a prize than B in the ratio 16 : 7. two of which are in their 1st year. where there is just one prize and two blanks.23 ≤ P(B ∩ C) ≤ 0. (a) Two cards are randomly drawn from a deck of 52 cards and thrown away. B. let P(A) = 0.21. What is the probability that a person seen smoking an ABC cigarette will be a man? 24. find their respective chances of winning.

33. A drawer contains 50 bolts and 150 nuts. 1 4 ( n − 3) : 2 5. A second purse contains 4 silver and 3 copper coins. 5 9 5 512 30. in γ as 5 . 16. 10 of which have blue eyes and the remaining 20 have brown hair. .2 3 28. 24. 35. 9:4 2 145 140 429 4. 9. prove that P(A ∩ B) ≤ P(A) ≤ P(A ∪ B) ≤ P(A) + P(B). 7 7 7 7 13 15. For any two events A and B. δ . (i ) 19 42 25 56 1 (ii ) 0. (b ) 23. Answers 1. in β as 3 . Half of the bolts and half of the nuts are rusted. 30 31 . 6. 61 61 (i ) 1 114 (ii ) 137 228 22. What is the probability that a student picked at random was able to see and hear satisfactorily? 3 2 34. The most unfortunate 30% fell into both of these categories. (b ) 8. 32. 7 . find the probability that exactly one of them will solve it. 34. A class consists of 80 students. (i ) 4 33 13 20 59 91 1 7 (ii ) 2 7 3. Of the students attending a lecture. 3 5 13000 39151 5 16 (i ) 1 4 (ii ) 79 120 (iii ) 11 120 2. If all three try to solve 3 the problem simultaneously. 1 13 16 39 20. An old purse contains 2 silver and 4 copper coins. 10. 61 90 . 107 120 4 2 1 . 46% 2 7 55 84 5 84 21. 17. He estimates his chance of passing in α 4 as 5 . 12. and 8 . 7. respectively. β . A student takes his examinations in four subjects α . what is the probability that it is a silver coin? 32. (i ) 1 35 24 35 (ii ) 2 7 29. (i ) (ii ) (iii ) 25. B. 25 of which are girls and 55 are boys. 5 8 2 5 (iii ) 31. The probabilities of A. 11. and in δ as 2 . To qualify he must pass in α and at least two other 3 6 4 subjects. 19. 35. blue-eyed girl? 33. γ . What is the probability that he qualifies? 36. What is the probability of selecting a brown-haired. If a coin is pulled out at random from one of the two purses. 27. C solving a problem are 1 . (a) 17 20 65 81 (a) . . 50% could not see what was written on the board and 40% could not hear what the lecturer was saying. If one item is chosen at random.1214 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 30. what is the probability that it is rusted or is a bolt? 31.

. . E2: the ball is drawn from bag Y and A: the ball is red. . The significance of Bayes’ Theorem may be understood in the following manner: P(Ei) is the probability of the occurrence of Ei. 2. . . . A bag X contains 2 white and 3 red balls and a bag Y contains 4 white and 5 red balls.50 BAYES’ THEOREM 1215 ________________________________________________________________________________________________________ 21. ∪ E n A = A∩S = A ∩ (E1 ∪ E 2 ∪ . . En are mutually exclusive and exhaustive events with P(Ei) ≠ 0. We have to find P(E2/A). Find the probability that it was drawn from bag Y. . Sol. . + P(E n )P(A/E n ) = ∑ P(E i )P(A/E i ) i =1 n [∵ A ⊂ S] [Distributive Law] ⇒ . . ∪ E n ) = (A ∩ E1 ) ∪ (A ∩ E 2 ) ∪ . . By Bayes’ Theorem. . (1) Now ⇒ P(A ∩ E i ) = P(A)P(E i / A) P(E i / A) = P(A ∩ E i ) P(E )P(A/E i ) = n i P(A) ∑ P(Ei )P(A/Ei ) i =1 [Using (1)] Note. P(E 2 )P(A/E 2 ) P(E 2 /A) = .21. n) of a random experiment then for any arbitrary event A of the sample space of the above experiment with P(A) > 0. . . . the probability P(Ei) is changed to P(Ei/A). ILLUSTRATIVE EXAMPLES Example 1. ∪ (A ∩ E n ) P(A) = P(A ∩ E1 ) + P(A ∩ E 2 ) + . (i = 1. . + P(A ∩ E n ) = P(E n )P(A/E1 ) + P(E 2 )P(A/E 2 ) + . En being exhaustive ∴ S = E1 ∪ E 2 ∪ . E2. The events E1. P(E1 ) = P(E 2 ) = 2 3 Also P(A/E1) = P(a red ball is drawn from bag X) = 5 5 P(A/E2) = P(a red ball is drawn from bag Y) = 9 . One ball is drawn at random from one of the bags and is found to be red. Let E1: the ball is drawn from bag X. E2. Let S be the sample space of the random experiment. we have P( Ei ) P( A / Ei ) P ( Ei / A) = n ∑ P( Ei ) P( A / Ei ) i =1 Proof. Bayes’ Theorem enables us to evaluate P(Ei/A) if all the P(Ei) and the conditional probabilities P(A/Ei) are known. . . . . . . The experiment is performed and we are told that the event A has occurred. (1) P(E1 )P(A/E1 ) + P(E 2 )P(A/E 2 ) 1 Since the two bags are equally likely to be selected.50 BAYES’ THEOREM If E1. With this information. . . . .

40 × 0. E3 : bag III is chosen and A : the two balls are white and red. Then P(E1) = 0.04 + 0. 5 black. B. Let E1. What is the probability that it was manufactured by machine B? Sol. What is the probability that they come from bags I. ∴ From (1). we have P(E 2 )P(H/E 2 ) P(E 2 /H) = P(E1 )P(H/E1 ) + P(E 2 )P(H / E 2 ) + P(E 3 )P(H / E 3 ) = 0. 1 black.25. P(H/E2) = 0.41. 35%.05 Similarly. 1 Now P(E1) = P(E2) = P(E3) = 3 1 C × 3 C1 1 = P(A/E1) = P (a white and a red ball are drawn from bag I) = 1 6 C2 5 2 P(A/E2) = 4 C1 × 1 C1 1 C1 × 3 C1 2 = . and C manufacture respectively 25%.35 × 0.04 0. One bag is chosen at random and two balls are drawn from it.25 × 0. E2 : bag II is chosen. and 40% of the total.02 By Bayes’ Theorem. The contents of bags I. and 3 red balls.04 and P(H/E3) = 0. P(E2/A) = P(E3/A) = . Of their output 5. and P(E3A). P(E2) = 0.0140 = = 0. 4.35 × 0. and 2 percent are defective bolts. II.· 118 59 . 2 white. and III are as follows: 1 white. B.02 0. and 3 red balls. and C respectively and let H denote the event of its being defective. 0.40 The probability of drawing a defective bolt manufactured by machine A is P(H/E1) = 0. Let E1 : bag I is chosen.35. 2 black. we have 1 1 × P(E1 )P(A / E1 ) 33 3 5 = = P(E1 / A) = P(E1 )P(A / E1 ) + P(E 2 )P(A / E 2 ) + P(E 3 )P(A / E 3 ) 1 × 1 + 1 × 1 + 1 × 2 118 3 5 3 3 3 11 55 15 Similarly.05 + 0. P(E3) = 0. and 1 red balls. and 4 white. In a bolt factory. we have P(E2/A) = 1 3 1 5 52 × + × 2 5 2 9 Example 2. or III? Sol.0345 Example 3. and E3 denote the events that a bolt selected at random is manufactured by the machines A. II. machines A. They happen to be white and red. E2. P(E2/A). We have to find P(E1/A). P(A / E 3 ) = 12 = 4 C2 3 C2 11 By Bayes’ Theorem.1216 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 1 5 × 25 2 9 = . A bolt is drawn at random from the product and is found to be defective.

. . 3. pn respectively. 3. An insurance company insured 2000 motorcycle drivers. all values of a continuous scale. 4. respectively. One of the insured persons has an accident. (ii) the number of aces in a draw of 2 cards from a well-shuffled deck is a random variable as it can take the values 0.03. 1.51 RANDOM VARIABLE If the numerical values assumed by a variable are the result of some chance factors. One of the bags is selected at random and a ball is drawn from it. 5 black balls. The probability of an accident is 0. p3. 4 black. What is the probability that he is a motorcycle driver? 5. usually from the last part of the alphabet. i. and 6000 truck drivers. Plant I manufactures 70% of scooters and plant II manufactures 30%. If the ball drawn is red. p2. 5. . 80% of the scooters are rated standard quality and at plant II. . respectively. 4 red. A scooter is chosen at random and is found to be of standard quality. Continuous and Discrete Random Variables A continuous random variable is one that can assume any value within an interval. . A company has two plants to manufacture scooters. 6 black. 2 5 27 83 3. find the probability that it is drawn from the (ii) second bag (i) first bag 2.15 respectively. 2% of the items produced by machine A were defective and 1% produced by machine B were defective. 2. (i) the number of heads in 4 tosses of a coin is a discrete random variable as it cannot assume values other than 0. for instance. Further. 3 4 ________________________________________________________________________________________________________ 21. Three bags contain 6 red. 1. For example (i) the weights (in kg) of a group of individuals. . Two bags contain 4 white. 21. find the probability that it is drawn from the first bag. One of the bags is selected at random and a ball is drawn from it. x2. Random variables are denoted by capital letters. the variable is then called a random variable. . If the ball drawn is white. . .21. 6 blue and 4 white. what is the probability that it was produced by machine A? 4. x3.. 4. (i ) 1 52 9 19 (ii ) 10 19 2. If a defective item is drawn at random.01. + pn = ∑p i =1 n i = 1. (ii) the heights of a group of individuals. etc. and 0. Y. 0. xn with probabilities p1. 4000 car drivers. and 5 red. X. A factory has two machines A and B. What is the chance that it has come from plant II? Answers 1. A discrete random variable is one that can assume only isolated values. 5 blue balls. 2 only. Z. .e. so that a particular value cannot be exactly predicted in advance. Past records show that machine A produced 60% of the items of output and machine B produced 40% of the items.52 DISCRETE PROBABILITY DISTRIBUTION Let a random variable X assume values x1. where P(X = xi) = pi ≥ 0 for each xi and p1 + p2 + p3 + . A random variable is also called a chance variable or a stochastic variable. 90% of the scooters are rated standard quality. . For example.52 DISCRETE PROBABILITY DISTRIBUTION 1217 ________________________________________________________________________________________________________ TEST YOUR KNOWLEDGE 1. At plant I.

then Standard deviation σ = + Variance. pn be a discrete probability distribution. It is not possible to just look at a bulb and tell whether or not it is defective. xn Σpi xi = Σpi xi Σpi Other names for the mean are average or expected value E ( X ) . P(X) : p1 . . x2 . Five defective bulbs are accidentally mixed with twenty good ones. x3 . or 4. We denote the variance by σ 2 and define σ 2 = Σpi ( xi − μ ) 2 We denote the mean by μ and define μ = P(X) : p1 . . . 2. . Number of defective bulbs = 5 Number of good bulbs = 20 Total number of bulbs = 25 P(X = 0) = P (no defective) = P (all 4 good ones) = 20 25 C4 20 × 19 × 18 × 17 969 = = C 4 25 × 24 × 23 × 22 2530 5 P(X = 1) = P(1 defective and 3 good ones) = C1 × 20 C3 1140 = 25 C4 2530 5 P(X = 2) = P(2 defectives and 2 good ones) = 5 C2 × 20 C2 380 = 25 C4 2530 C3 × 20 C1 40 P(X = 3) = P(3 defectives and 1 good one) = = 25 C4 2530 P(X = 4) = P(all 4 defectives) = 5 25 C4 1 = C4 2530 3 4 1 2530 ∴ The probability distribution of the random variable X is X : 0 969 2530 1 1140 2530 2 380 2530 40 2540 P(X) : . 21. . Let X denote the number of defective bulbs out of four. . . x3 . 1. . 3. Find the probability distribution of the number of defective bulbs. . . Clearly. X can take the values 0. .1218 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ X : x1 . xn p3 . . (∵ Σpi = 1) If μ is not a whole number.53 MEAN AND VARIANCE OF RANDOM VARIABLES Let X : x1 . x2 . σ 2 = Σpi xi2 − μ 2 ILLUSTRATIVE EXAMPLES Example 1. pn is called the discrete probability distribution for X and it spells out how a total probability of 1 is distributed over several values of the random variable. . p2 . if four bulbs are drawn at random from this lot. Sol. . . p3 . . p2 .

2 Sol. x : 0 1 2 3 4 5 6 7 2 2 2 p(x) : 0 k 2k 2k 3k k 2k 7k + k (i) Find k. 3 3 Example 3. P(X ≥ 6). (ii) Evaluate P(X < 6). 2. A success is “getting 1 or 6” on a toss. Let X denote the number of successes. A random variable X has the following probability function: Values of X. (i) Since x=0 ∑ p( x) = 1. Sol. Clearly X can take the values 0.53 MEAN AND VARIANCE OF RANDOM VARIABLES 1219 ________________________________________________________________________________________________________ Example 2. we have [∵ p ( x) ≥ 0] 7 ⇒ ⇒ 0 + k + 2k + 2k + 3k + k2 + 2k2 + 7k2 + k = 1 10k2 + 9k – 1 = 0 ⇒ (10k – 1)(k + 1) = 0 1 k= 10 .21. P(3 < X ≤ 6) (iii) Find the minimum value of x so that P(X ≤ x) > 1 . or 3. Probability of failure = 1 − = 6 3 3 3 2 2 2 8 P(X = 0) = P (no success) = P (all 3 failures) = × × = 3 3 3 27 1 2 2 12 P(X = 1) = P (1 success and 2 failures) = 3 C1 × × × = 3 3 3 27 1 1 2 6 P(X = 2) = P (2 successes and 1 failure) = 3 C2 × × × = 3 3 3 27 1 1 2 6 P(X = 3) = P (all 3 successes) = × × = 3 3 3 27 ∴ The probability distribution of the random variable X is X : 0 1 2 3 P(X) : 8 27 12 27 6 27 1 27 To find the mean and variance xi pi pi xi pi xi2 0 1 2 3 8 27 12 27 6 27 1 27 0 12 27 12 27 3 27 1 0 12 27 24 27 9 27 5 3 Mean μ = Σpi xi = 1 5 2 Variance σ 2 = Σpi xi2 − μ 2 = − 1 = . Find the mean and the variance of the number of successes. A die is tossed three times. 1. 2 1 1 2 Probability of success = = .

from this bag. 3. and σ for the number of red balls drawn. 5. P(X ≥ 3). Getting a number greater than 4 is considered a success. + P(X = 5) = 0 + k + 2k + 2k + 3k + k2 = 8k + k2 = 8 1 81 + = 10 100 100 P(X ≥ 6) = P(X = 6) + P(X = 7) 9 1 19 + = = 2k 2 + 7 k 2 + k = 100 10 100 P(3 < X ≤ 6) = P(X = 4) + P(X = 5) + P(X = 6) 3 3 33 = = 3k + k 2 + 2k 2 = + 10 100 100 1 1 3 1 < . 2. Find the probability distribution of the number of bad eggs in 3. 2 6. A bag contains 4 white and 3 red balls. P(X ≤ 2) = k + 2k = < (iii) P(X ≤ 1) = k = 10 2 10 2 5 1 8 1 P(X ≤ 3) = k + 2k + 2k = = . from this lot.1220 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ (ii) P(X < 6) = P(X = 0) + P(X = 1) + . X 0 625 1296 1 500 1296 2 150 1296 3 20 1296 4 1 1296 : P(X) : 0 12 22 1 9 22 2 1 22 . x p(x) : : 0 a 1 3a 2 5a 3 7a 4 9a 5 11a 6 13a 7 15a 8 17a (i) Determine the value of a. with replacement. drawn at random. without replacement. 4. (ii) Find P(X < 3). Find the variance of the probability distribution of the number of successes. Two cards are drawn simultaneously from a well-shuffled deck of 52 cards. . Three balls are drawn. Find μ . . Find the standard deviation for the following discrete distribution: x p( x) : : 8 1 8 12 1 6 16 3 8 20 1 4 24 1 12 Answers 1. P(2 ≤ X < 5) (iii) What is the smallest value of x for which P(X ≤ x) > 0.5? 7. A random variable X has the following probability distribution: Values of X. Find the probability distribution of the number of doubles in four throws of a pair of dice. Two bad eggs are mixed accidently with 10 good ones. P(X ≤ 4) = k + 2k + 2k + 3k = > 10 2 10 2 ∴ The maximum value of x so that P(X ≤ x) > 1 is 4. Compute the variance for the number of aces. 2 TEST YOUR KNOWLEDGE 1. A die is tossed twice. X : P(X) : 2. σ .

S r times n F F F .55 BINOMIAL PROBABILITY DISTRIBUTION 1221 ________________________________________________________________________________________________________ 3. If a certain hypothesis is assumed. . . 9 9 27 4. but we shall consider only three that are of great importance: (i) Binomial Distribution (or Bernoulli’s Distribution).21. Let the trials be independent and p be constant for every trial. . .. 400 5. (ii) Poisson’s Distribution. 4 9 (i ) a = 1 81 2873 1 8 7 (ii ) .. P(X = r) is usually written as P(r). . There are many types of theoretical frequency distributions. Let us find the probability of r successes in n trials. (iii) Normal Distribution. Let a random variable X denote the number of successes in these n trials. .. Such distributions are called Theoretical Distributions. 1. q ( n − r ) factors = Cr p q n r n−r Hence P(X = r) = nCr qn–rpr. . . . . The distribution (1) is called the binomial probability distribution and X is called the binomial variate. Observed frequency distributions are based on actual observation and experimentation. 6. Note 1. where p + q = 1 and r = 0. BINOMIAL (OR BERNOULLI’S) DISTRIBUTION 21. ________________________________________________________________________________________________________ 21. ∴ P(X = r ) = n Cr P (S S S) .54 THEORETICAL DISTRIBUTIONS Frequency distributions can be classified under two heads: (i) Observed Frequency Distributions. . 7 49 7 2 5 (iii ) 5 7. 9 36 6 . . F ( n − r ) times = Cr P(S)P(S) . Let p be the probability of a success and q be that of a failure in a single trial so that p + q = 1. (ii) Theoretical or Expected Frequency Distributions.55 BINOMIAL PROBABILITY DISTRIBUTION Let there be n independent trials in an experiment. . r successes can be obtained in n trials in nCr ways. 2. P(F) r factors ( n − r ) factors = Cr p p p . n.. P(S) P(F)P(F) . . p n r factors q q q . it is sometimes possible to derive mathematically what the frequency distribution of a certain universe should be. .

. nCnpn which are the successive terms of the binomial expansion of (q + p)n. + Cn −1 p n −1 ⎤ ⎣ ⎦ = nq n −1 p + 2 ⋅ = np(q + p) n −1 = np (∵ p + q = 1) . 21. . if P(0) is known. The successive probabilities P(r) in (1) for r = 0. P(3).56 RECURRENCE OR RECURSION FORMULA FOR THE BINOMIAL DISTRIBUTION In a binomial distribution. P(r ) = n Cr q n − r p r Mean μ = ∑ rP(r ) = ∑ r ⋅ n Cr q n − r p r r =0 r=0 = 0 + 1⋅ C1q n n −1 p + 2 ⋅ n C 2 q n − 2 p 2 + 3 ⋅ n C3 q n −3 p 3 + . n and p occurring in the binomial distribution are called the parameters of the distribution. . . . Note 3. . In a binomial distribution: (i) n. (iii) all the trials are independent. . That is why this distribution is called the “binomial” distribution.57 MEAN AND VARIANCE OF THE BINOMIAL DISTRIBUTION n n For the binomial distribution. + np n 2 ⋅1 3 ⋅ 2 ⋅1 n(n − 1)(n − 2) n −3 3 = nq n −1 p + n(n − 1)q n − 2 p 2 + q p + . .1222 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Note 2. . (iv) p (and hence q) is constant for all the trials. . . (ii) each trial has only two possible outcomes usually called success and failure. Applying this formula successively. . . + p n −1 ⎥ 2 ⋅1 ⎣ ⎦ n −1 n −1 n −1 n−2 n −1 n −3 2 n −1 = np ⎡ C0 q + C1q p + C2 q p + . P(2). = 21. nC1qn–1p. 1. . . nC2qn–2p2. . . . the number of trials is finite. 2. we can find P(1). . n! q n−r p r (n − r )!r ! n! q n − r −1 p r +1 P(r + 1) = n Cr +1q n − r −1 p r +1 = (n − r − 1)!(r + 1)! r! p P(r + 1) (n − r )! = × × P(r ) (n − r − 1)! (r + 1)! q P(r ) = n Cr q n − r p r = ∴ r! p (n − r ) × (n − r − 1)! ⎛ n−r ⎞ p × × ×=⎜ ⎟⋅ (n − r − 1)! (r + 1) × r ! q ⎝ r +1 ⎠ q n−r p ⇒ P(r + 1) = ⋅ P(r ) r +1 q which is the required recurrence formula. + n ⋅ n C n p n n(n − 1) n − 2 2 n(n − 1)(n − 2) n −3 3 q p + 3⋅ q p + . n are n C0qn. . Note 4. + np n 2 ⋅1 (n − 1)(n − 2) n −3 2 ⎡ ⎤ = np ⎢ q n −1 + (n − 1)q n − 2 p + q p + . . .

. npq npq γ 1 = β1 = = 1− 2 p npq γ 2 = β2 − 3 = 1 − 6 pq npq 1 2 gives a measure of skewness of the binomial distribution. γ 1 = q− p npq 1 2 μ32 (q − p)2 (1 − 2 p )2 1 − 6 pq μ = = . if p > .21. . β2 = 3 + 1 − 6 pq npq gives a measure of the kurtosis of the binomial distribution.57 MEAN AND VARIANCE OF THE BINOMIAL DISTRIBUTION 1223 ________________________________________________________________________________________________________ Hence the variance of the binomial distribution is np. If p < 1 2 . . What was the probability that exactly 3 out of a convoy of 6 ships would arrive safely? 1 8 1 Sol. Standard deviation of the binomial distribution is npq . n = 6 9 9 9 ⎛1 8⎞ Binomial distribution is ⎜ + ⎟ ⎝9 9⎠ 6 ⎛ 1 ⎞ ⎛ 8 ⎞ 10240 . . β2 = 4 = 3 + 3 2 npq npq npq μ2 μ2 q − p 1− 2 p = . . skewness is positive. Similarly. ILLUSTRATIVE EXAMPLES Example 1. + n(n − 1) n Cn p n ] − μ 2 n(n − 1) n − 2 2 n(n − 1)(n − 2) n −3 3 ⎡ ⎤ = μ + ⎢ 2 ⋅1 ⋅ q p + 3⋅ 2 ⋅ q p + . + p n − 2 ] − μ 2 = μ + n(n − 1) p 2 [ n − 2 C0 q n − 2 + n − 2 C1q n −3 p + . . . . we can prove that β1 = Hence Note. . One ship out of 9 was sunk on an average in making a certain voyage. + n − 2 Cn − 2 p n − 2 ] − μ 2 = μ + n(n − 1) p 2 (q + p ) n − 2 − μ 2 = μ + n(n − 1) p 2 − μ 2 = np + n(n − 1) p 2 − n 2 p 2 = np[1 + (n − 1) p − np ] = np[1 − p ] = npq. it is zero. = μ + [2 ⋅1 ⋅ n C2 q n − 2 p 2 + 3 ⋅ 2 ⋅ n C3 q n −3 p 3 + . . [∵ q + p = 1] [∵ μ = np ] Hence the variance of the binomial distribution is npq. the probability of a ship arriving safely = 1 − = . skewness is negative and if p = . Variance σ 2 = ∑ r 2 P(r ) − μ 2 = ∑ [r + r (r − 1)]P(r ) − μ 2 r =0 n r=0 n n = ∑ rP(r ) + ∑ r (r − 1)P(r ) − μ 2 = μ + ∑ r (r − 1) n Cr q n − r p r − μ 2 r =0 r =0 r=2 n n (since the contribution due to r = 0 and r = 1 is zero). p. The probability that exactly 3 ships arrive safely = 6 C3 ⎜ ⎟ ⎜ ⎟ = 96 ⎝9⎠ ⎝9⎠ 3 3 . + n(n − 1) p n ⎥ − μ 2 2 ⋅1 3 ⋅ 2 ⋅1 ⎣ ⎦ n−2 2 n −3 3 n 2 = μ + [n(n − 1)q p + n(n − 1)(n − 2)q p + . q = . + n(n − 1) p ] − μ = μ + n(n − 1) p 2 [q n − 2 + (n − 2)q n −3 p + .

Six dice are thrown 729 times. the probability of a telephone number being busy between 2 P. n = 6. and 3 P.M. p. and 3 P. ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ Example 3. p = the chance of getting 5 or 6 with one die = = 6 3 1 2 q = 1 − = . how many families would be expected to have (i) 2 boys and 2 girls (ii) at least one boy (iii) no girl (iv) at most two girls? Assume equal probabilities for boys and girls. on 1 week-days = 15 1 14 ⎛ 14 1 ⎞ q = 1 − = . Out of 800 families with 4 children each.1224 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Example 2. How many times do you expect at least three dice to show a five or six? 2 1 Sol. Sol. Assume that on the average one telephone number out of fifteen called between 2 P.M.9997 6 (15) (15)6 6 6 5 4 2 3 3 The probability that at least three of them will be busy = p(3) + p(4) + p(5) + p(6) ⎛ 14 ⎞ ⎛ 1 ⎞ ⎛ 14 ⎞ ⎛ 1 ⎞ ⎛ 14 ⎞ ⎛ 1 ⎞ ⎛1⎞ = 6 C3 ⎜ ⎟ ⎜ ⎟ + 6 C4 ⎜ ⎟ ⎜ ⎟ + 6 C5 ⎜ ⎟ ⎜ ⎟ + 6 C6 ⎜ ⎟ = 0. q = probability of having a girl = 2 2 .M. on week-days is busy. n = 6. Since probabilities for boys and girls are equal 1 1 p = probability of having a boy = . (ii) at least three of them will be busy? Sol. 3 3 2 4 5 6 ⎛ 2 1⎞ The binomial distribution is N(q + p) = 729 ⎜ + ⎟ ⎝ 3 3⎠ The expected number of times at least three dice will show five or six ⎡ 6 ⎛ 2 ⎞ 3 ⎛ 1 ⎞ 3 6 ⎛ 2 ⎞ 2 ⎛ 1 ⎞ 4 6 ⎛ 2 ⎞ ⎛ 1 ⎞5 6 ⎛ 1 ⎞ 6 ⎤ = 729 ⎢ C3 ⎜ ⎟ ⎜ ⎟ + C4 ⎜ ⎟ ⎜ ⎟ + C5 ⎜ ⎟ ⎜ ⎟ + C6 ⎜ ⎟ ⎥ ⎝ 3⎠ ⎝3⎠ ⎝ 3⎠ ⎝3⎠ ⎝ 3 ⎠⎝ 3 ⎠ ⎝3⎠ ⎥ ⎢ ⎣ ⎦ 729 = 6 [160 + 60 + 12 + 1] = 233 3 n 6 Example 4.005. Binomial distribution is ⎜ + ⎟ 15 15 ⎝ 15 15 ⎠ The probability that not more than three will be busy = p(0) + p (1) + p(2) + p(3) 6 ⎛ 14 ⎞ ⎛ 14 ⎞ ⎛ 1 ⎞ ⎛ 14 ⎞ ⎛ 1 ⎞ ⎛ 14 ⎞ ⎛ 1 ⎞ = C0 ⎜ ⎟ + 6 C1 ⎜ ⎟ ⎜ ⎟ + 6 C2 ⎜ ⎟ ⎜ ⎟ + 6 C3 ⎜ ⎟ ⎜ ⎟ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ ⎝ 15 ⎠ 3 (14) 2744 × 4150 = [2744 + 1176 + 210 + 20] = = 0. What is the probability that if 6 randomly selected telephone numbers are called (i) not more than three.M. N = 729 3 3 since dice are in sets of 6 and there are 729 sets.

A product is 0. If the chance that one of the ten telephone lines is busy at an instant is 0..e. four or more will suffer from the disease? 5. What is the probability of: (i) losing one ship (ii) losing at most two ships (iii) losing none. What is the probability that out of ten men now 60.5% defective and is packed in cartons of 100. find the probability that (i) exactly two will be defective (iii) none will be defective. 16 4 (iii) The expected number of families having no girl. N = 800 ∴ The binomial distribution is 800 ⎜ + ⎟ . ⎝2 2⎠ (i) The expected number of families having 2 boys and 2 girls 1 ⎛1⎞ ⎛1⎞ = 800 C2 ⎜ ⎟ ⎜ ⎟ = 800 × 6 × = 300.e. ⎝2⎠ 4 (iv) The expected number of families having at most two girls. find the probability that out of 5 vessels expected to arrive. The probability that a man aged 60 will live to be 70 is 0. 2. The probability of any ship of a company being destroyed on a certain voyage is 0.. The probability that a pen manufactured by a company will be defective is 1 10 . at least 7 would live to be 70? 4. having 4 boys ⎛1⎞ = 800 ⋅ C4 ⎜ ⎟ = 50.57 MEAN AND VARIANCE OF THE BINOMIAL DISTRIBUTION 1225 ________________________________________________________________________________________________________ ⎛1 1⎞ n = 4. 16 ⎝2⎠ ⎝2⎠ ⎝ 2 ⎠⎝ 2 ⎠ ⎝2⎠ ⎥ ⎢ ⎣ ⎦ TEST YOUR KNOWLEDGE 1. Find the probability of getting at least seven heads. The company owns 6 ships for the voyage.02. What percentage contains not more than 3 defectives? . 16 ⎝2⎠ ⎝2⎠ 4 2 2 4 (ii) The expected number of families having at least one boy ⎡ 4 ⎛ 1 ⎞3 ⎛ 1 ⎞ 4 ⎛ 1 ⎞ 2 ⎛ 1 ⎞ 2 4 ⎛ 1 ⎞ ⎛ 1 ⎞3 4 ⎛ 1 ⎞ 4 ⎤ = 800 ⎢ C1 ⎜ ⎟ ⎜ ⎟ + C2 ⎜ ⎟ ⎜ ⎟ + C3 ⎜ ⎟ ⎜ ⎟ + C4 ⎜ ⎟ ⎥ ⎝2⎠ ⎝2⎠ ⎝2⎠ ⎝2⎠ ⎝ 2 ⎠⎝ 2 ⎠ ⎝2⎠ ⎥ ⎢ ⎣ ⎦ = 800 × 1 [4 + 6 + 4 + 1] = 750. Ten coins are tossed simultaneously. i. having at least 2 boys 2 2 3 4 ⎡ 1 ⎛1⎞ ⎛1⎞ ⎛ 1 ⎞⎛ 1 ⎞ ⎛1⎞ ⎤ = 800 ⎢ 4 C2 ⎜ ⎟ ⎜ ⎟ + 4 C3 ⎜ ⎟ ⎜ ⎟ + 4 C4 ⎜ ⎟ ⎥ = 800 × [6 + 4 + 1] = 550.21. at least 4 will arrive safely. i. What is the probability that out of six workers chosen at random. 8.2 (i) What is the chance that 5 of the lines are busy? (ii) What is the probability that all the lines are busy? 7. The incidence of occupational disease in an industry is such that the workers have a 20% chance of suffering from it. (ii) at least two will be defective 6. 3.65. If on an average 1 vessel in every 10 is wrecked. If 12 such pens are manufactured.

If four balls are drawn successively (with replacement) from the bag.432 + 0. The following data are the number of seeds germinating out of 10 on a damp filter for 80 sets of seeds.2833 99. 20. 14. 10.2301 (ii) 0.1085 (ii) 0.1226 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ 9. 13.8 for five trials. with replacement. 4. a player has to cross 10 hurdles. In a hurdle race. A bag contains 10 balls each marked with one of the digits 0 to 9. 11. and 8 black balls. find the probability that all the tickets bear numbers divisible by 10.83 100 (0. 0. how many families would be expected to have (i) 3 boys and 2 girls. A box contains 100 tickets each bearing one of the numbers from 1 to 100. The probability that a ball thrown by a child will strike a target is 1 5 .514 (i) 0. Here n = 10. 9. find the distribution. how many would be expected to contain at least 3 defective parts? Answers 1. Fit a binomial distribution for the following data and compare the theoretical frequencies with the actual ones: x f : : 0 2 1 14 2 20 3 34 4 22 5 8 3 2 12. In 800 families with 5 children each. 5. find the probability of obtaining at least 1 20 2 28 3 12 4 8 ∴ np = 2. Out of 1000 such samples. Fit a binomial distribution to this data: x : 0 f : 6 . 11. (ii) 2 boys and 3 girls. If the sum of mean and variance of a binomial distribution is 4.) 15.024 × 10–7 (i ) 81 256 (ii ) 5 1 256 (iii ) 175 256 (iv ) 27 128 ⎜ ⎟ 2⎝6⎠ ⎛1+ 4⎞ ⎜ ⎟ ⎝5 5⎠ 11 32 . 6. (ii) at least two will strike the target. what is the probability that none is marked with the digit 0? [Hint. 8. 12.175 etc. In 100 sets of ten tosses of an unbiased coin. If six balls are thrown find the probability that (i) exactly two will strike the target. If the mean of a binomial distribution is 3 and the variance is 4 successes. The probability that he will clear each hurdle is What is the probability that he will knock down fewer than 2 hurdles? . what is the probability that (i) none is white (iii) at least one is white (ii) all are white (iv) only 2 are white? 5 6 10. N = 80. (Assume probabilities for boys and girls to be equal. Mean = 5 6 Σ fx 6 0 7 0 8 0 9 0 10 0 Total 80 18.8858 (i) 0. A bag contains 5 white.02579 (ii) 1. 7 red. 13.91854 5⎛5⎞ 9 2. If 5 tickets are drawn successively (with replacement) from the box. in how many cases do you expect to get (i) 7 heads and 3 tails (ii) at least 7 heads? 16. the mean number of defectives in a sample of 20 is 2. In sampling a large number of parts manufactured by a machine. 11 64 53 3125 0. 7. (iii) no girl (iv) at the most two girls. If four balls are drawn one by one.3412 (iii) 0. 19.] Σf 17.568)5 3.9997 (iii) 0. (i) 0.

for a binomial distribution P(X = r ) = n Cr q n − r p r n(n − 1)(n − 2) . the Naperian base. 17. Now. say λ . we can find the distribution.21. . .58 POISSON DISTRIBUTION AS A LIMITING CASE OF BINOMIAL DISTRIBUTION 1227 ________________________________________________________________________________________________________ 14. if we assume that as n → ∞ and p → 0 such that np always remains finite. ⎜1 − ⎟ tends to 1. (n − r + 1) ⎜ n ⎟ ⎝ ⎠ = × × r r r! n ⎛ λ⎞ ⎜1 − ⎟ ⎝ n⎠ ⎛ λ⎞ 1− r λ ⎛ n ⎞ ⎛ n −1 ⎞ ⎛ n − 2 ⎞ ⎛ n − r +1 ⎞ ⎜ n ⎟ ⎝ ⎠ = ⎜ ⎟⎜ ⎟× ⎟⎜ ⎟ . ∴ x →∞ ⎢⎝ n ⎠ ⎥ ⎝ x⎠ ⎣ ⎦ → e − λ as n → ∞ .58 POISSON DISTRIBUTION AS A LIMITING CASE OF BINOMIAL DISTRIBUTION If the parameters n and p of a binomial distribution are known. 18. . .345 ________________________________________________________________________________________________________ POISSON DISTRIBUTION 21. (i) 12 nearly (ii) 17 nearly ⎛9⎞ ⎜ ⎟ ⎝ 10 ⎠ 4 (i) 0. the application of the binomial distribution is very laborious. But in situations where n is very large and p is very small.00001 323 15. .2175)10 0. Also n ⎠ ⎝ n⎠ ⎝ n⎠ ⎝ x ⎛ λ⎞ ⎜1 − ⎟ tends to 1. 20. (n − r + 1) ⎛ λ ⎞ = × ⎜1 − ⎟ r! ⎝ n⎠ n−r ⎛λ⎞ ×⎜ ⎟ ⎝n⎠ n r since np = λ ∴ p = λ n ⎛ λ⎞ 1− r λ n(n − 1)(n − 2) . ⎜1 − ⎟ .. . 19. . (i) 250 (ii) 250 (iii) 25 (iv) 400 80 (0. .246 (ii) 0. . (n − r + 1) = × (1 − p ) n − r × p r r! n(n − 1)(n − 2) . ⎝ n⎠ −λ r n ⎡ ⎤ ⎛ 1⎞ ⎛ λ ⎞λ ⎥ ⎢⎜ 1 − ⎟ Since Lt ⎜1 + ⎟ = e. we get the Poisson approximation to the binomial distribution. ⎜1 − ⎟× r r! ⎝ n ⎠⎝ n ⎠ ⎝ n ⎠ ⎛ λ⎞ ⎜1 − ⎟ ⎝ n⎠ As n → ∞ . 16. each of the (r – 1) factors n −λ ⎛ 1⎞ ⎛ 2⎞ ⎛ r −1 ⎞ ⎜1 − ⎟ .7825 + 0. .⎜ r ! ⎝ n ⎠ ⎝ n ⎠ ⎝ n ⎠ ⎝ n ⎠ ⎛ λ ⎞r ⎜1 − ⎟ ⎝ n⎠ n − ⎤ ⎡ λ⎞ λ⎥ ⎢⎛ 1 − ⎟ ⎢⎜ n ⎠ ⎥ λ r ⎛ 1 ⎞ ⎛ 2 ⎞ ⎛ r − 1 ⎞ ⎣⎝ ⎦ = ⎜1 − ⎟ ⎜1 − ⎟ . . .. However.

. 1. 1.1228 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Hence in the limiting case when n → ∞. + + . = e −λ + λe −λ 1! + λ e 2 2 −λ 2! + 3 λe 3 −λ 3! +. −λ =e −λ ⎛ λ λ λ ⎞ ⎜1 + + + + .. . . (A) x x2 xn Note 2. . to ∞. 2. Note 1. 2. since P(0) + P(1) + P(2) + P(3) + . . 21..59 RECURRENCE FORMULA FOR THE POISSON DISTRIBUTION For the Poisson distribution. . ⎟ = e 1! 2! 3! ⎝ ⎠ ⋅ e = 1. . 3. 3. . . e = 1 + + . P(r ) (r + 1)! r + 1 r +1 This is called the recurrence formula for the Poisson distribution.60 MEAN AND VARIANCE OF THE POISSON DISTRIBUTION For the Poisson distribution. .⎥ − λ 2 2! 3! 4! ⎣ 1! ⎦ ⎡ 2λ 3λ 2 4λ 3 ⎤ = λ e − λ ⎢1 + + + + . (A) represents the Poisson probability distribution. is 1. . . the mean of the Poisson distribution is equal to the parameter λ . λ is called the parameter of the distribution. 1. ⎟ = λ e− λ ⋅ eλ = λ ⎝ 1! 2! ⎠ Thus. 2. . . P(r ) = Mean μ ∞ ∞ λ r e− λ r! = ∑ rP(r ) = ∑ r ⋅ r =0 r=0 λ r e− λ r! = e−λ ∑ ⎛ ⎞ λ2 λ3 = e−λ ⎜ λ + + + . . . . . . . . λ 21.⎥ − λ 2 2! 3! ⎣ 1! ⎦ . The sum of the probabilities P(r) for r = 0. . . .⎟ 1! 2! r = 1 ( r − 1)! ⎝ ⎠ ∞ λr ⎛ λ λ2 ⎞ = λ e− λ ⎜1 + + + . . ) r! where λ is a finite number = np. 3. we have (r = 0. . P(X = r ) = λ r e−λ . 1! 2! n! x Note 3. Variance σ 2 r 2λ r = ∑ r P(r ) − μ = ∑ r ⋅ −λ = e ∑ − λ2 r! r =0 r =0 r =1 r ! ∞ 2 2 ∞ 2 2 −λ ∞ λ r e− λ ⎡12 ⋅ λ 22 ⋅ λ 2 32 λ 3 42 λ 4 ⎤ = e−λ ⎢ + + + + . P(r ) = ∴ λ r e−λ r! and P(r + 1) = λ r +1e − λ (r + 1)! P(r + 1) λr ! λ λ = = or P(r + 1) = P(r ). . r = 0.

⎥ − λ 2 1! 2! 3! ⎣ ⎦ 2 3 2 ⎡ ⎞ ⎛ λ 2λ ⎞⎤ λ λ λ 3λ 3 −λ ⎛ = λ e ⎢⎜ 1 + + + + .⎟⎥ − λ 2 3! ⎠ ⎝ 1! 2! ⎠⎦ ⎣⎝ 1! 2! 3! ⎡ ⎛ λ λ2 ⎞⎤ = λ e − λ ⎢ eλ + λ ⎜1 + + + . The mean and the variance of the Poisson distribution can also be derived from those of the binomial distribution in the limiting case when n → ∞. . n = 200. 3 3 4 2 Example 2. λ . . 4 from the recurrence relation of the Poisson distribution.21. . . . we get 2 P(1) = 2P(0) = 2 × 0. . 2.1804. Hence. Note.0902. ∴ Mean of the Poisson distribution = Lt np = Lt λ = λ n→∞ n→∞ Variance of the binomial distribution is npq = np (1 – p) ⎛ λ⎞ ∴ Variance of the Poisson distribution = Lt np (1 − p ) = Lt λ ⎜ 1 − ⎟ = λ . Sol. (1) r +1 r +1 λ r e− λ e −2 Now P(r ) = ⇒ P(0) = = e −2 = 0. 3 in (1). find the probabilities for r = 1. Here p= = = 0. 1 200 1 . p → 0 and np = λ . the variance of the Poisson distribution is also λ . ⎟⎥ − λ 2 ⎝ 1! 2! ⎠⎦ ⎣ −λ λ λ −λ 2 = λ e [e + λ e ] − λ = λ e ⋅ eλ (1 + λ ) − λ 2 = λ (1 + λ ) − λ 2 = λ. ∴ λ = np = Sol. Assume that the probability of an individual coal miner being injured in a certain way in a mine accident during a year is 1/2400. If the variance of the Poisson distribution is 2.083) r e −. Use Poisson’s distribution to calculate the probability that in a mine employing 200 miners there will be at least one such similar accident in a year. 3.083 ∴ = P(r ) = r! r! . . . the mean and the variance of the Poisson distribution are each equal to the parameter λ . . . Thus.1353 r! 0! Setting r = 0.60 MEAN AND VARIANCE OF THE POISSON DISTRIBUTION 1229 ________________________________________________________________________________________________________ ⎡ (1 + 1)λ (1 + 2)λ 2 (1 + 3)λ 3 ⎤ = λ e − λ ⎢1 + + + + .1353 = 0. n→∞ n →∞ ⎝ n⎠ ILLUSTRATIVE EXAMPLES Example 1. Mean of binomial distribution is np.2706.2706 2 2 2 2 1 P(3) = P(2) = × 0.083 2400 2400 12 λ r e − λ (0. P(2) = P(1) = 0.2706 = 0.1804 = . 2.⎟ + ⎜ + + + . P(4) = P(3) = × 0. 1. the parameter of the Poisson distribution = Variance = 2 Recurrence relation for the Poisson distribution is λ 2 P(r + 1) = P(r ) = P(r ) .

7 108. showing the number of injuries from horse kicks in each of the 200 army corps.92 = 0.61) r (0. (e–1.7 4! 20 4 1 Total = 200 Example 4.7 × r! r! r! r 0 1 P(r) 108.7 × 0.083) = 1 − P(0) = 1 − (0.1 3! (0.61) 4 108. A car rental firm has two cars.2231) Sol.61) r (0.61 ⋅ = 200 × 0. mr e− m where N = Σ f = 200 ∴ Required Poisson distribution is N ⋅ r! (0.5. of injuries Frequency : : 0 109 1 65 2 22 3 3 4 1 Total 200 Fit a Poisson distribution to the data and calculate the theoretical frequencies: Σ fx 65 + 44 + 9 + 4 122 = = = 0.5. ∴ Proportion of days on which neither car is used = Probability of there being no requests for a car m0e− m = e −1.61 Sol.7 × (0.2231 0! Proportion of days on which some requests are refused = probability for the number of requests to be more than two = ⎛ me − m m 2 e − m ⎞ = 1 − P( x ≤ 2) = 1 − ⎜ e − m + + ⎟ 1! 2! ⎠ ⎝ .1230 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ P(at least one fatal accident) = 1 – P(no fatal accident) (0.61) 2 = 20.83 = 1 − .7 × = 0.5 = 0.61 = 66.08.5435 = 108.2 2! (0.083)0 e −0. which it hires out day by day. The distribution of injuries was as follows: No.5 = 0. Mean of given distribution = Σf 200 200 This is the parameter (m) of the Poisson distribution.61) 2 . Since the number of requests for a car is distributed as a Poisson distribution with mean m = 1. = 200e −0. The number of requests for a car on each day is distributed as a Poisson distribution with mean 1. 0! Example 3.7 × = 4. Calculate the proportion of days on which neither car is used and the proportion of days on which some requests are refused.3 Theoretical Frequency 109 66 2 3 4 108.61)3 108. Data was collected over a period of 10 years.

60 MEAN AND VARIANCE OF THE POISSON DISTRIBUTION 1231 ________________________________________________________________________________________________________ ⎛ (1. Using the Poisson distribution. Fit a Poisson distribution to the following and calculate theoretical frequencies: x f : : 0 122 1 60 2 15 3 2 4 1 9.8087375 = 0. If P(X = 2) = P(X = 1) find. 4. of cells per sq. Suppose that X has a Poisson distribution.1912625. and packs them in boxes of 500. A certain screw-making machine produces on average 2 defective screws out of 100. (i) P(X = 0) (ii) P(X = 3). five or more will suffer from it? 8. Probability of getting one head with one coin = 1 . m x e − m (100) x ⋅ e −100 = .5 + ⎟ = 1 − 0. find the standard deviation. The incidence of occupational disease in an industry is such that the workmen have a 10% chance of suffering from it.625 = 1 − 0. What is the probability that in a group of 7. Example 5. 3. Six coins are tossed 6400 times. If a random variable has a Poisson distribution such that P(1) = P(2).2231 (1 + 1. Fit a Poisson distribution to the following data given the number of yeast cells per square for 400 squares: No.125) 2 ⎠ ⎝ = 1 − 0.21. 6. Find the probability that a box contains 15 defective screws. Show that in a Poisson distribution with unit mean. .2231× 3.5 + 1.001. If the probability of a bad reaction from a certain injection is 0. : No. 2 1 ⎛1⎞ ∴ The probability of getting six heads with six coins = ⎜ ⎟ = ⎝ 2 ⎠ 64 ∴ Average number of six heads with six coins in 6400 throws = np = 6400 × ∴ The mean of the Poisson distribution = 100. find (i) mean of the distribution (ii) P(4) 2 3 5. x! (100)! TEST YOUR KNOWLEDGE 1. Sol. Fit a Poisson distribution to the following: 6 1 = 100 64 Approximate probability of getting six heads x times when the distribution is Poisson = x : f : 0 192 1 100 2 24 3 3 4 1 2.5 ⎜1 + 1. If X is a Poisson variate such that P(X = 2) = 9P(X = 4) + 90P(X = 6). of squares : 0 103 1 143 2 98 3 42 4 8 5 4 6 2 7 0 8 0 9 0 10 0 ⎛2⎞ 10. determine the chance that out of 2000 individuals more than two will get a bad reaction.5) 2 ⎞ = 1 − e −1. determine the approximate probability of getting six heads x times. mean deviation about mean is ⎜ e ⎟ times the ⎝ ⎠ standard deviation. 7.

and two defective blad respectivel in a des ly shipment of 10000 packets. 121. μ and σ . The tw tails of th curve ext n wo he tend to + ∞ and – ∞ toward the positive and negative d directions of the x-axis respectivel and gradu ly ually approach the x-axis s without e ever meeting it. 13. oisson distribu ution to calculate the approx ximate number of packets contain ning no defecti ive.5) ) 5 6. 3. If a variable x has the nor rmal distribu ution with m mean μ and standard d d deviation σ . The cu g urve is unimodal and the e mode of the normal distribution coincides w its mean with n 1 ⎛ x−μ ⎞ 2 . If the errors are r ook ges 3 al ese randomly distr ributed throughout th book. Out of a group of 40 men. It is bell-shaped and symme etrical abou ut the mean μ . there is a sma chance of 0. 0 respective ely 0. e rom the bino omial distributi in the lim ion miting case w when n. what i the probabili that 10 page selected at r he is ity es. __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ NORMAL DISTRIB N BUTION 21.018. 1 (10) e 15 −1 10 4. now ag 35 years. called t paramete of d the ers where the variable x can assume all values fr the distri ibution. is close to 1 . 15. The g general equat tion of the no ormal distrib bution is giv by ven 2 − ⎜ ⎟ 1 f ( x) = e 2⎝ σ ⎠ σ 2π e rom – ∞ to + ∞ . 3. r! Theoretical fre equencies are 1 61. In a certain factory turning razor blades. (15)! = 0. 1. 3. (i) e–4 (ii) 4e–4 e . 142 92. w is the pro f 00 ged what obability that 2 men will die w within the next 5 yea ars? 13. ability of a success. Suppose a bo of 585 pag contains 43 typographica errors.503 (9 9. 12.503) r r! (ii) 2. 12. x is calle the normal variate an f ( x) is c ed nd called the pr robability de ensity function of the norma distributio al on. 0.01936 Theoreti frequencies are ical 109.61 NORMAL DISTRIBUTIO N ON The normal distribution is a continuou distributio It can be derived fr us on. 320 × e 0. 0 0.4795 121.002 for any blade to be defe f g all fective. the number of trials is very large and p the proba y p. 7.1232 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ 11.36 × (0. The graph of th normal d he distribution is called the e normal c curve. The blades are supplied in packets of 1 Use the Po a n 10. σ > 0. 8. (i) 2 2 3e 2 5. we 2 briefly w write x : N( μ . 0 0.0008 9802. 2. where r = 0 1. 40. 2. random. are respectively the mean and the sta y andard devia ation of the distribution and n – ∞ < μ < ∞ .32 3. σ ). 4 0. 11. 9. will b free from err be rors? Answers 1.035 0. The probability that a man aged 35 years will die before reaching the age of 40 ye may be tak as s e ears ken 0. 196. 2 0. 0. one defective. 13. 1 .

21. A sample of 10 dry batter cells teste to find th length of life produce the s 00 ry ed he ed following results: g x = 12 hou σ = 3 ho urs. the median of the distribu e ution also coincides with its mean an mode. .63 ST TANDARD FOR OF THE NO RM ORMAL DISTR RIBUTION 1233 __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ μ . The m mean. the total are under the normal curv above the x-axis is 1. ts (iv) It is a unim ) modal distribu ution. The random variable Z is called t the ndard ) norm random variable. ps mpute areas u under the no ormal proba ability It is free from any paramete This help us to com curve by making use of standard tables. x i. where F(z ) = ∫ F( z z −∞ f ( x)dz = P(Z ≤ z ) function F(z) defined above i called the dis d is stribution func ction for the no ormal distributi ion. tal er l ve 21. ours.63 STANDARD FORM OF THE NORM S D MAL DISTRIBUTION If X is a norma random v al variable with mean μ a h and standard deviation σ .e. ILLUSTRA ATIVE EXAMP PLES Exa ample 1. ea e ve e (iii) The norma distribution is symmetr ) al n rical about it mean. and median of this distr n ribution coin ncide. The proba e abilities P(z1 ≤ Z ≤ z 2 ). P(z1 < Z ≤ z 2 ). Thus. e F(− z1 ) = 1 − F( z1 ). then th random variable Z = he X−μ has h the nor rmal distrib bution with mean 0 a and σ standard deviation 1. If f ( z ) is the probability density functi for the norm distributio then e y ion mal on. The l x = μ divides the ar under the normal cur above th x-axis into two equal p line d rea e rve he o parts. Note 1.21. The tot area unde the normal curve abov the x-axis is 1. standard dized (or stan mal The probability density f y function fo the norm or mal distributi in standa form is g ion ard given by 1 − 1 z2 f ( z) = e 2 2π s a er. Note 3. P(z1 ≤ Z ≤ z2 ) = ∫ z2 z1 f ( z )dz = F z2 )F( z1 ). The f Note 2. mode.62 BASIC PRO B OPERTIES O THE NOR OF RMAL DISTRIBUTION 1 ⎛ x−μ ⎞ σ ⎟ ⎠ 2 The probability density func ction of the n normal distribution is giv by ven − ⎜ 1 f ( x) = e 2⎝ σ 2π (i) f ( x) ≥ 0 (ii) ) ∫ ∞ −∞ f ( x)dx = 1.. Th area unde the h nd he er normal c curve betwee any two given ordin en nates x = x1 and x = x2 represents th probabili of he ity values fa alling into the given inter e rval. P( z1 ≤ Z < z 2 ) an P( z1 < Z < z 2 ) are all reg nd garded to be the sa ame.

.9σ ∴ σ = 10 Sub btracting From (1).D. z = – 2 . otes gth x − x x − 12 Also o = z= .42 5 From the tables. (1) . Let x and σ be the me and S.31 = 0. . e o area is 0.08 = 0. le z =z1 P(z1 < z < 0) = 0.28%.1587 = 15.5 − 0.1234 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ Assu uming the da to be nor ata rmally distri ibuted. .5[ z1 < 0] ∴ en et Whe x = 64.4974 = 49.34 = 0. ⇒ Area to the left of the or rdinate x = 4 is 0. nding to this area is 1.5 × 10 − 5 ∴ x = 50.31 45 en et Whe x = 45. (2) . Sol. the value of z correspon m . z = 3 P(10 < x < 14 P 4) = P(−0. . le z = z2 P(0 < z < z2) = 0. ∴ P( x < 6) = Pz < −2) = P(0 > 2) = P < z < ∞) − P(0 < z < 2 P(0 2) = 0. what percentage of battery c t cells are expected to have li ife (i) more than 15 hours ) (ii) less than 6 hour s rs (iii) between 10 and 14 hou ) 0 urs? Sol.4.0228 = 2. 31% of the item are under 4 % ms 45.5 – 0. z = 1 ∴ P( x > 15) = P( z > 1) = P(0 < z < ∞) − P(0 < z < 1) = 0.5 z1 = −0.67) = 2 × 0.67 3 2 en = 0. er Find the mean and st tandard devi iation of the distribution n. 5 σ and 1.5 – 0.5 − 0.4 x−x Sinc ce z= σ −0. In a normal di istribution.67 Whe x = 14. Here x deno the leng of life of dry battery cells.19 5 From the tables the value of z corresponding to this m s.5σ and d 64 − x = 1. respectivel ean ly.4σ 4 −19 = −1. z = − = – 0. σ 3 (i) W When x = 15.2487 = 0.87%.67 7) = 2P(0 < z < 0.67 < z < 0.4 = 4 64 − x σ . 413 7 (ii) W When x = 6. 4 Exa ample 2.74%. 2 2 (iii) When x = 10.4772 = 0. 3 31% of the i items are un nder 45 and 8% are ove 64. s z2 = 1.5 = 45 − x ⇒ 5 45 − x = −0. m 45 − x = −0.

Let X denote the number of scores on a test.2% (iii) 84% ________________________________________________________________________________________________________ SAMPLING AND TESTS OF SIGNIFICANCE 21. (i) 252 (ii) 533 6. 6. In a normal distribution. e.21. Assuming normal distribution for the scores. x = 50.33 (i) 50% (ii) 21. 300 0.g.M. 5.. An aptitude test for selecting officers in a bank is conducted on 1000 candidates. What are the mean and standard deviation of the distribution? 4. A universe containing a finite number of individuals or members is called a finite inverse: for example. Assuming the heights are normally distributed. the universe of the weights of students in a particular class. 7. 5. have a mean of 352 and a standard deviation of 31. and 4 P. 3. If X is normally distributed with mean 100 and standard deviation 15. we may even be ignorant whether or not a particular universe is infinite.64 POPULATION OR UNIVERSE 1235 ________________________________________________________________________________________________________ TEST YOUR KNOWLEDGE 1. Their grades were found to be normally distributed with mean 60 and standard deviation 5. the universe of pressures at various points in the atmosphere. The mean height of 500 students in a certain college is 151 cm and the standard deviation is 15 cm. the universe of stars. Find approximately: (i) How many will pass. It is thus a collection of individuals or of their attributes (qualities) or of results of operations that can be numerically specified.? 6.06% 3. What percentage of the time will there be more than 400 telephone calls made in this community between 3 P.M. In an examination taken by 500 candidates. What percent of students scored (i) more than 60 grades? (iii) between 45 and 65 grades? (ii) less than 56 grades? 7. σ = 10. how many students have heights between 120 and 155 cm? 2.3. In some cases.9772 (i) 79 (ii) 35% (iii) 11 2. A universe with an infinite number of members is known as an infinite universe: for example.M. The average score is 42 and the standard deviation of score is 24. find (i) The number of candidates whose scores exceed 60 (ii) The number of candidates whose scores lie between 30 and 60.64 POPULATION OR UNIVERSE An aggregate of objects (animate or inanimate) under study is called population or universe. 4. if 50% is fixed as a minimum? (ii) What should be the minimum if 350 candidates are to pass? (iii) How many have scored above 60%? Answers 1. Students of a class were given a mechanical aptitude test. and 4 P.M. the average and the standard deviation of grades obtained (normally distributed) are 40% and 10%. 7% of the items are under 35 and 89% are under 63. . It is known from past experience that the number of telephone calls made daily in a certain community between 3 P. find the probability that X does not exceed 130.

An attempt is thus made through sampling to give the maximum information about the parent universe with the minimum effort. apples.65 SAMPLING The statistician is often confronted with the problem of discussing a universe of which he cannot examine every member. If t is any statistic.e. The theory of sampling is a study of the relationship existing between a population and samples drawn from the population.E. the question arises: What can be said about a universe of which we can examine only a limited number of members? This question is the origin of the Theory of Sampling. The process of selecting a sample from a universe is called sampling. by taking a spoonful of it. the variance. The fundamental object of sampling is to get as much information as possible about the whole universe by examining only a part of it. Naturally. 21. A sample is thus a small portion of the universe. or any other commodity by taking only a handful of it from the bag and then decide whether to purchase it or not. The statistical concepts of the sample from the members of the sample to estimate the parameters of the population from which the sample has been drawn are known as statistics. It plays an important role in the theory of large samples and it forms a basis of the testing of hypotheses.(t ) p Q n1 . The collection of all possible ways in which a specified event can happen is called a hypothetical universe. in a store we assess the quality of lettuce.). for a large sample z= t − E(t ) is normally distributed with mean 0 and variance 1.66 PARAMETERS OF STATISTICS The statistical constants of the population such as mean. The number of individuals in a sample is called the sample size. S. Population mean and variance are denoted by μ and σ 2 . while those of the sample are given by x and s 2 . if we want to have an idea of the average per capita income of the United States. enumeration of every earning individual in the country is a very difficult task.E.. etc. i. of which complete enumeration is impracticle. 21. A chef normally tastes cooked products to find if they have been properly cooked and contain the proper quantity of salt or sugar.1236 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ The universe of concrete objects is an existent universe.) The standard deviation of the sampling distribution of a statistic is known as the standard error (S.67 STANDARD ERROR (S. 21. Sampling is quite often used in our day-to-day practical life. For example. n2 For a large sample. For example. the standard errors of some of the well-known statistics are listed below: n σ 2 s2 sample size population variance sample variance population proportion =1–p sizes of two independent random samples .E. The universe of heads and tails obtained by tossing a coin an infinite number of times (provided that it does not wear out) is a hypothetical one. A finite sub-set of a universe is called a sample. are known as the parameters.

4. Hence alternative hypotheses help to know whether the test is a two-tailed test or a onetailed test. The probability α that a random value of the statistic t belongs to the critical region is known as the level of significance. 21. if we want to test the null hypothesis that the population has a specified mean μ0 . whether (i) the deviation between the observed sample statistic and the hypothetical parameter value or (ii) the deviation between two sample statistics is significant or might be attributed due to chance or the fluctuations of the sampling. we first set up a hypothesis that is a definite statement about the population parameter called the Null hypothesis denoted by H0. 2. Statistic Standard error 1. 6. 21. which will enable us to decide. is called the critical region or the region of rejection.70 LEVEL OF SIGNIFICANCE The probability of the value of the variate falling in the critical region is known as the level of significance. 5. . Any hypothesis that is complementary to the null hypothesis (H0) is called an Alternative hypothesis denoted by H1. The region of the sample space S that amounts to the acceptance of H0 is called the acceptance region. 21. (ii) H1 : μ > μ0 (right-tailed alternative hypothesis (or) single-tailed). then we have H0 : μ = μ 0 Alternative hypotheses will be (i) H1 : μ ≠ m0 ( μ > μ0 or μ < μ0 ) (two-tailed alternative hypothesis). in the sample space S that amounts to rejection of the null hypothesis H0.69 CRITICAL REGION A region corresponding to a statistic t. 3. For example.70 LEVEL OF SIGNIFICANCE 1237 ________________________________________________________________________________________________________ No.21. (iii) H1 : μ < μ0 (left-tailed alternative hypothesis (or) single-tailed). on the basis of the results of the sample. To apply the tests of significance.68 x s σ/ n σ 2 / 2n σ 12 n1 + + 2 σ2 Difference of two sample means x1 − x2 Difference of two sample standard deviations s1 − s2 Difference of two sample proportions p1 − p2 Observed sample proportion p n2 2 σ2 σ 12 2n1 2n2 P1Q1 P2 Q 2 + n1 n2 PQ/n TEST OF SIGNIFICANCE An important aspect of the sampling theory is to study the test of significance.

Typ II Error. 2 p ( z > zα ) = a.71 ERRORS IN SAMPLING E N G The main goal of the samp pling theory is to draw a valid conc clusion abou the popul ut lation paramete on the ba of the s ers asis sample resul In doing this we ma commit th following two lts. also referred to as consum o mer’s risk. the variab z = he ble is norm mally S. we may reject it. .e. 21. from equation (1).. p ( z > zα ) = α / 2 i. P(A Accept H0 wh it is wro hen ong) = P(Ac ccept H0/H1) = β . . When H0 is t pe W true. The critical valu of zα of t test statistic at level of significan α for a two-tailed t is ue the nce test given by p ( z > zα ) = α . T value of z (as given previously under the null The f n y) e hypothes is known as the test s sis statistic. i ailed.E t ) E.. ay he g types of e errors: Typ I Error.e.1238 CHAPTER 21: STATISTICS AND PROBAB BILITY __________ ______________ _____________ ______________ ______________ _____________ ______________ ______________ ______ P(t ∈ ω | H 0 ) = α i.e. This value is dependent o (i) the l s d on level of sig gnificance u used and (ii) the altern i native hypothes whether it is one-tailed or two-ta sis. When H0 is wrong we m accept it pe may t. (1) o ea tical region on both tails is α .e. a referred to as produ ype also d ucer’s risk. i. Sinc the s ce i. the le of signi evel ificance is th size of the type I error or the maxi he e r imum produ ucer’s risk. β is called the size of the ty II ype error. t − E t) E( For larger samp ples corresp ponding to th statistic t. y P(R Reject H0 whe it is true) = P(Reject H0/H0) = α en α is called the size of the ty I error... we get p ( z > zα ) + p ( z < − zα ) = α .( distribute with mea 0 and va ed an ariance 1. the a of each tail is α / 2. Critical v values or si ignificant va alues The values of th test statis that sepa he stic arate the crit tical region and the acceptance regi is ion called the critical va e alues or the s significant v value. zα is the value of z so that the total are of the crit normal curve is symm metrical. area t .

(t ) Step 5: Conclusion. t − E(t ) Step 4: Test statistic. Step 2: Alternative hypothesis. the following are the important tests of significance. Set up H0 in clear terms. Testing of significance for a single mean.72 TESTING OF SIGNIFICANCE FOR A SINGLE PROPORTION This test is used to find the significant difference between the proportion of the sample and the population. p(z < – zα ) = α if it is left tailed. 21. Compute the test statistic z = under the null hypothesis. etc.58 zα = 2. TEST OF SIGNIFICANCE FOR LARGE SAMPLES If the sample size n > 30. Testing of significance for a single proportion.645 Two-tailed test Right-tailed Left-tailed zα = 2.33 zα = 1.645 zα = 1. p ( z < − zα ) = α Level of significance 1% (0. Testing of significance for a difference of proportions.05) z = 1. Using the equation and the normal tables. Select the appropriate level of significance in advance depending on the reliability of the estimates. If z < zα . 2. we reject H0 and conclude that there is significant difference. are closely approximated by normal distributions assuming the population as normal.33 zα = −2. 1.01) 5% (0. The critical value of z for a single-tailed test (right or left) at the level of significance α is the same as the critical value of z for a two-tailed test at the level of significance 2α . 3.28 zα = −1. The following steps may be adopted to test statistical hypotheses: Step 1: Null hypothesis. If z > zα .645 zα = −1.1) z = 0. the critical value of z at a different level of significance ( α ) for both single-tailed and two-tailed tests are calculated and listed below. S. Step 3: Level of significance. the sample is taken as a large sample.E. p ( z > zα ) = α . Poisson. . Set up H1 so that we can decide whether to use the onetailed test or the two-tailed test. Compare the computed value of z with the critical value zα at the level of significance ( α ). as Binomial. Under a large sample test.72 TESTING OF SIGNIFICANCE FOR A SINGLE PROPORTION 1239 ________________________________________________________________________________________________________ The critical value zα is that value such that the area to the right of zα is α / 2 and the area to the left of – zα is α / 2. The equations are p ( z > zα ) = α .28 Note.21.966 10% (0. we accept H0 and conclude that there is no significant difference. For such a sample we apply a normal test. Testing of significance for a difference of means. In the case of the one-tailed test p ( z > zα ) = α if it is right tailed. chi-square. 4.

i. i.5. . The probable limit for the observed proportion of successes is p ± zα PQ/n . Q = 1 – P = Probability of failure. Test the hypothesis that the coin is unbiased. E(X) = nP.5 Here n = 400.e.z= = ∼ N(0. z < zα . If α is not given.6 0.. P ≠ 0. zα is the significant value of z at 5% level of significance.5 p−P under H0.5. Conclusion. . Q = 1 – P = 1 – 0. we can take safely 3σ limits.( p) = .54 p = proportion of success in the sample n 400 population proportion = 0. H0: The coin is unbiased. E(p ) = p n n 1 1(PQ) V( p) = V(X/n) = 2 v(X) = = PQ/n n n PQ p − E(p) p− p S. PQ n zα is the pq / n . Sol.1240 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Let X be the number of successes in n independent trials with constant probability P of success for each trial.e. V(X) = nPQ.54 − 0. 1 np E(x) = = p. Let p = X/n called the observed proportion of success. I.e. X = No. Since z = 1.. 1) SE(p) n PQ/n E(p) = E(X/n) = This z is called the test statistic that is used to test the significant difference of sample and population proportion. P = 0. the limits for the proportion in the population are p ± zα Note 3. Hence. q = 1 – p.E.5 = 1..5 = P. H1: The coin is not unbiased (biased). test statistic z = PQ/n 0. ILLUSTRATIVE EXAMPLES Example 1.5 = 0.96 z = I. If p is not known. the coin is unbiased in P = 0.e.6 < 1. Note 2. Note 1.. A coin was tossed 400 times and returned heads 216 times. of success = 216 X 216 = = 0. the confidence limits for the observed proportion p are p ± 3 The confidence limits for the population proportion p are p ± pq n . where significant value at level of significance α .5 × 0.5 400 we use the two-tailed test.

03496 PQ 1 2 1 × × The test statistic n 3 3 9000 z = 0. Accept the hypothesis As z < zα . zα is the tabulated value of z at 5% level of significance.04.03496 < 1.5 > 1.96 Conclusion. the claim of the manufacturer is accepted. Example 4. Under H0. A random sample of 600 products contained 36 defectives.04 then (right tailed). 36 = 0.21.04 H0 : p = 0. Since z = 2.5.5 > 1. i.96 600 Conclusion. we conclude that the die is unbiased. A certain cubical die was thrown 9000 times and a 5 or a 6 was obtained 3240 times.. I.06 600 p = proportion of defectives in the population = 0. Sol.e.. do the data indicate an unbiased die? Sol.04 × 0.06 − 0.e. z= 0.96. A manufacturer claims that only 4% of his products supplied are defective. z = 2. A machine is producing bolts of which a certain fraction is defective. P = proportion of defectives in the sample = I. we apply the right-tailed test. ∵ H0 is accepted. Test the claim of the manufacturer.33 z= = = 0. PQ/n 0. only if p > 0.645 ( zα ) so we reject the null hypothesis here also. Does this indicate that the proportion of defectives is larger than that claimed by the manufacturer who claims that only 5% of his products are defective? Find the 95% confidence limits of the proportion of defective bolts in the batch. the manufacturer’s claim is not acceptable. On the assumption of unbiased throwing. If H1 is taken as p > 0. . Here n = 9000 P = probability of success (i.. we reject the hypothesis H0 at 5% level of significance two tailed..e.04 p−P = = 2. A random sample of 400 is taken from a large batch and is found to contain 30 defective bolts.e. Example 3. getting a 5 or a 6 in the throw of the die) P = 2/6 = 1/3.36 n 9000 H0 : is unbiased.04 (two-tailed test) (ii) If we want to reject.72 TESTING OF SIGNIFICANCE FOR A SINGLE PROPORTION 1241 ________________________________________________________________________________________________________ Example 2. Q = 1 – 1/3 = 2/3 X 3240 p= = = 0.36 − 0. (i) P = observed proportion of success.04 is true. In both cases. P = 1/3 H1 : P ≠ 1/3 (two-tailed test) p−P 0. H1 : (i) P ≠ 0.

02865).02865 400 Hence 95% confidence limits for the proportion of defective bolts are (0. 100 Since the confidence limit is not given. Here p = proportion of defective articles = = 0.1. we assume it is 95%.05 (right-tailed test). and out of them 540 are vegetarian and the rest are nonvegetarian.96 Example 5.e.1588. q = 1 – p = 1– 0.96 100 Hence.2941.07136. i. TEST YOUR KNOWLEDGE 1.05 ± 0.075 400 0.05 ± 1. 2. In a city. A random sample of 500 bolts was taken from a large shipment and 65 were found to be defective. 0. i.0588 = 0. p = observed proportion of sample = Under H0. Also the proportion of population P is not given.05 p−P ∴ z= = 2.1 = 0.075 − 0.05 × 0.1588. 0. A sample of 600 people selected at random from a large city shows that the percentage of males in the sample is 53.07136.9. Find the limits for the proportion of defective articles in the bag. 0. H0 : The manufacturer’s claim is accepted.5.0412. P = 5 = 0.96. Find the percentage of defective bolts in the shipment. a sample of 1000 people was taken. A bag contains defective articles.645. The tabulated value of z at 5% level of significance for the right-tailed test is zα = 1. It is believed that the ratio of males to the total population in the city is 0. p > 0.95 400 Conclusion. 0. Can we say that both habits of eating (vegetarian or non-vegetarian) are equally popular in the city at (i) 1% level of significance (ii) 5% level of significance? 3. A sample of 100 from the bag gives 10 defective articles.05 × 0. the exact number of which is not known.. 325 men out of 600 men chosen from a big city were found to be smokers. Since z = 2. Test whether the belief is confirmed by the observation. To find 95% confidence limits of the proportion.95 Alternative hypothesis. which is given by P ± pq / n = 0.1× 0. the test statistic z = 30 = 0. PQ/n 0. 0.05 = 0. the 95% confidence limits for the defective articles in the bag are (0. To get the confidence limit.02135 = 0.645.e.9 = 0. H0 is rejected at 5% level of significance.2941 > 1.05 100 Q = 1 – P = 1 – 0. 0. Does this information support the conclusion that the majority of men in the city are smokers? 4. ∴ level of significance is 5% zα = 1.1 ± 0.95 = 0.0412).1242 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Sol.. the proportion of defective bolts is larger than the manufacturer claims.1 ± 1. it is given by p ± zα PQ/n 0. we use P. Null hypothesis. 10 Sol. .

5 ________________________________________________________________________________________________________ 21. H0 accepted at 5% level H0 rejected at 5% level H0 accepted at 5% level 2. 800 people were known to be tea drinkers in a sample of 1200 people. n1 = 500 p2 = = 0. H1 : p1 > p2 (right-tailed test) p1 − p2 0. 8 3⎛ 1 1 ⎞ ⎛1 1⎞ × ⎜ + PQ ⎜ + ⎟ ⎟ 11 11 ⎝ 1000 1200 ⎠ n1 n2 ⎠ ⎝ Conclusion. After overhauling the machine it produced 3 defectives in a batch of 100.842. Since the calculated value of z > 1. n1 + n2 ⎛1 1⎞ PQ ⎜ + ⎟ ⎝ n1 n2 ⎠ ILLUSTRATIVE EXAMPLES Example 1.645 also z > 2. 800 people out of a sample of 1000 people were found to be tea drinkers. yields p1 − p2 n p +n p z= .73 TEST OF DIFFERENCE BETWEEN PROPORTIONS 1243 ________________________________________________________________________________________________________ 5. 4. i. i. The test statistic under the null hypothesis H0.73 TEST OF DIFFERENCE BETWEEN PROPORTIONS Consider two samples X1 and X2 of sizes n1 and n2 respectively taken from two different populations. Do you think that there has been a significant decrease in the consumption of tea after the increase in the excise duty? Sol.5 : 11.6666 The test statistic z = = = 6.8 − 0. = 100 500 100 . Example 2. 400 apples are taken at random from a large basket and 40 are found to be bad.. p2 = 2 = = n1 1000 5 n2 1200 3 p1n1 + p2 n2 X1 + X 2 800 + 800 8 3 = = = . 475 female and 525 male babies were born in a week. 3. there is no significant difference in the consumption of tea before and after the increase of excise duty. 6.032.51 and 8. Hence H0 is rejected.Q= n1 + n2 n1 + n2 1000 + 1200 11 11 Null hypothesis H0. Here n1 = 800. p1 = = 0.33. n2 = 1200 p1 = P= X1 800 4 X 800 2 = = . where P = 1 1 2 2 and Q = 1 − P. Before an increase in the excise duty on tea. Has the machine improved? 16 3 Sol. there is a significant decrease in the consumption of tea due to the increase in excise duty. After an increase in the duty.. In a hospital. n2.e. H0 rejected at 5% level. A machine produced 16 defective articles in a batch of 500.e. Answers 1. both the significant value of z at 5% and 1% level of significance.21. 5. accepted at 1% level Between 17. We test the significance of the difference between the sample proportion p1 and p2.49 8. p1 = p2. Estimate the proportion of bad apples in the basket and assign limits within which the percentage most probably lies.03. Do these figures confirm the hypothesis that males and females are born in equal numbers? 6. that there is no significant difference between the two sample proportion.

015 1 ⎞ ⎛ 1 0. n1 = 500.645. 1 ⎞ ⎛1 1⎞ ⎛ 1 (0. the significant value of z at 5% level of significance. i..01692 × 0. However < 2. 800 similar articles from a second factory are only found to be 1. H0 is accepted. H0 : Sample proportions are equal. p2 = 25% = 0.032 − 0. 500 articles from a factory are examined and found to be 2% defective. the products do not differ in quality. i.7 0. The calculated value of z < 1. the test statistic p1 − p2 0. Since z > 1. The machine has not improved due to overhauling.3 − 0. Q1 = 0. H1 : p1 ≠ p2 z= P1 − P2 = P1Q1 P2 Q 2 + n1 n2 z 0. H0 is accepted.3 × 0. As z < 1. the difference in population proportions is likely to be hidden in sampling. Q2 = 0. ..7.03 z= = = 0. z= ⎛1 1⎞ PQ ⎜ + ⎟ ⎝ n1 n2 ⎠ P= z= n1 p1 + n2 p2 0. the products do not differ in quality.9830 n1 + n2 500 + 800 0.e.75.104. H1 : p1 < p2 (one-tailed test) p1 − p2 Under H0..01692.e. p n + p2 n2 19 H1 : p1 > p2 (right tailed) ∴ P = 1 1 = ≅ 0.015 H0 : There is no significant difference between the two products.02(500) + (0. i.5% defective. Q = 1 − P = 0. In two large populations there are 30% and 25% respectively of fair-haired people.5376. At 5% level these samples will reveal the difference in the population proportions..032 n1 + n2 600 Under H0. Is this difference likely to be hidden in samples of 1200 and 900 respectively from the two populations? Sol. 0. p1 = p2. Can it be reasonably concluded that the products of the first factory are inferior to those of the second? Sol.58. H0 is accepted.1244 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Null hypothesis H0.983 ⎜ + ⎟ ⎝ 500 800 ⎠ = 0. the significant value of z at 1% level of significance. p1 = proportion of fair-haired people in the first population = 30% = 0.968) ⎜ + PQ ⎜ + ⎟ ⎟ ⎝ 500 100 ⎠ n1 n2 ⎠ ⎝ Conclusion.3.032)(0.02 − 0. n2 = 800 p1 = proportion of defective products from the first factory = 2% = 0.02 p2 = proportion of defective products from the second factory = 1.e. H0 is rejected.25 × 0.25.68 Conclusion. Example 4.25 = 2.96. the machine has not improved due to overhauling. i. the significant value of z at 5% level of significance.e. the significant value of z at 5% level of significance.645.015)(800) = = 0.75 + 1200 900 Conclusion.5% = 0. Example 3.

Answers ________________________________________________________________________________________________________ 1. Under the null hypothesis that there is no difference between the sample mean and the population mean x −μ the test statistic is z = .74 TEST OF SIGNIFICANCE FOR THE SINGLE MEAN To test whether the difference between the sample mean and the population mean is significant or not: Let X1. i.58 These limits are called confidence limits or fiducial limits. 200 men and 325 women were in favor of the proposal.5% was males while in towns A and B combined. 500 men and 320 women voted yes. σ n < μ < x + 1. to test whether the difference between the sample mean and population mean is significant or not. In a referendum submitted to the student body at a university. XN of size N with mean μ and variance σ 2 ∴ the standard error of mean of a random sample of size n from a population with variance σ 2 is σ / n .. 2.21. At 5% of level of significance. test whether the 8% difference is a valid claim. 21. this proportion in a total of 1406 births was 0. we use the test statistic z = s/ n the sample. .96 At 1% level of significance. Test the hypothesis that the proportion of men and women in favor of the proposal is the same at 5% level of significance.74 TEST OF SIGNIFICANCE FOR THE SINGLE MEAN 1245 ________________________________________________________________________________________________________ TEST YOUR KNOWLEDGE 1. . H0 : accepted. 99% confidence limits are x − 2. where s is the standard deviation of If σ is not known. A manufacturing firm claims that its brand A product outsells its brand B product by 8%. Note. H0 : accepted 2. there were 956 births of which 52. H0 : rejected 3.e. Xn be a random sample of size n from a large population X1. . 850 men and 560 women voted.496. . X2. where σ is the standard deviation of the population.58 σ n . Is there any significant difference in the proportion of male births in the two towns? 3. X2. A random sample of 400 men and 600 women was asked whether they would like to have a school near their residence. If it is found that 42 out of a sample of 200 people prefer brand A and 18 out of another sample of 100 people prefer brand B. σ n < μ < x + 2. . 95% confidence limits are x − 1. . . . Does this indicate a significant difference of opinion between men and women on this matter at 1% level? 4. σ/ n X−μ . In a town A.96 σ n . H0 : accepted 4.. If the level of significance is α and zα is the critical value − zα < z = x −μ < zα σ/ n The limits of the population mean μ are given by x − zα σ n < μ < x + zα σ / n . To test whether the given sample of size n has been drawn from a population with mean μ .

4. H0 : Assume that the sample is drawn from a large population with mean 3.67 = 0. x = 3. of the weight distribution of the population is 3 gms. and n = 400 x −μ 6.96.1246 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ ILLUSTRATIVE EXAMPLES Example 1.e. Is the difference significant? Sol. μ = 3.) x −μ 3.3. Here n = 100. Example 2.. H0 is rejected.2 and S.8.2 cms and S. Can it be reasonably regarded as a sample from a large population of mean 3.226. σ = 3.2. μ = 50.3 cms? Sol.5...774. 63. H0 : There is no significant difference between x and μ . Example 3.5 / 900 σ/ n Conclusion. The average grades in mathematics of a sample of 100 students was 51 with a S. H1 : μ ≠ 3.8 and standard deviation of 1.25 (Apply two-tailed test. Sol. the sample is not drawn from the population with mean 67. σ is unknown. Here n = 100.75. Could this have been a random sample from a population with average grades of 50? Sol.e. 2.D. i.3.96 the significant value of z at 5% level of significance.4 − 3.75 − 6. H0 : There is no significant difference between sample and population mean. A random sample of 900 wooden sticks has a mean of 3. the sample is drawn from the population with μ = 67 H1 : μ ≠ 67 (Two-tailed test) x −μ 64 − 67 = = −10 ∴ z = 10. The 99% confidence limits is given by x ± 2.75. μ = 67. Also set up 99% confidence limits of the mean weight of the population.58 ×3 / 100 = 64. z = σ / n 2. x = 51.3.261. x = 6.67 1. z = σ / n 3 / 100 Conclusion. Example 4.D. σ = 2.D. A normal population has a mean of 6. Under H0. the sample is drawn from the population with mean 3. H0 is accepted. The mean weight obtained from a random sample of size 100 is 64 gms. = 2. Since the calculated value of z > 1. the significant value of z at 5% level of significance. i.e.261 < 1. H1 : There is significant difference between x and μ . i. A sample of 400 members gave a mean of 6. I.2 = = 0. there is no significant difference between x and μ .D.e. μ = 50 H1 : μ ≠ 50 . As the calculated value of z = 0.96 at 5% level of significance.D.8 = = − 0. Under H0. Here n = 900.5.3 / 900 Conclusion. s = 6. Given μ = 6.2 and S. H0 : The sample is drawn from a population with mean 50. Test the statement that the mean weight of the population is 67 gms at 5% level of significance.58 σ / n = 64 ± 2. As the calculated value of z < zα = 1. x = 64. H0 is z = accepted. σ = 1. μ = 67. of 6. = 2.4 cms.. The S.

of 125 hours.2 5. The guaranteed average life of a certain type of bulb is 1000 hours with a S. H0 accepted 3. If σ 1 . A random sample of 200 measurements from a large population gave a mean value of 50 and a S.666 < 1. Answers 1.5 cms? 3. H0 rejected at 1% to 5% level of significance.e. of 20 pounds. i. ________________________________________________________________________________________________________ 21.e. Test the hypothesis that the mean height of college students in the city is 160 cms. A sample of 400 male students is found to have a mean height of 160 cms.D.96. n = 4 2. σ 12 n1 + 2 σ2 n2 Under the null hypothesis that the samples are drawn from the same population where σ 1 = x1 − x2 σ 2 = σ . 48.D. μ1 = μ2 the test statistic is given by z = .. Determine 95% confidence interval for the mean of the population. Could the mean weight of students in the population be 120 pounds? 2. Can it be reasonably regarded as a sample from a large population with mean height 162. . we use σ = 2 n1 s1 + n2 s2 2 2 n1 + n2 to calculate σ . If σ is not known and σ 1 = σ 2 . It is decided to sample the output so as to ensure that 90% of the bulbs do not fall short of the guaranteed average by more than 2. A sample of 1000 students from a university was taken and their average weight was found to be 112 pounds with a S.D. n2 Note 2.D. A sample of 1000 students has a mean height of 158 cms. TEST YOUR KNOWLEDGE 1.75 TEST OF SIGNIFICANCE FOR DIFFERENCE OF MEANS OF TWO LARGE SAMPLES 1247 ________________________________________________________________________________________________________ x −μ 51 − 50 10 = = = 1. 1 1 + σ n1 n2 Note 1.75 TEST OF SIGNIFICANCE FOR DIFFERENCE OF MEANS OF TWO LARGE SAMPLES Let x1 be the mean of a sample of size n1 from a population with mean μ1 and variance σ 12 . H0 is accepted. 4.5 cms and standard deviation 4. The test statistic is given by z = . zα the significant value of z at 5% level of sig- Under H0..5%. s / n 6 / 100 6 Conclusion. Let x2 be the mean of an independent sample of size n2 from another population with mean μ2 x1 − x2 2 and variance σ 2 .21. σ 2 are not known and σ 1 ≠ σ 2 the test statistic in this case is z = x1 − x2 s1 2 n1 + s2 2 . Since z = 1.8 and 51. of 9. the sample is drawn from the population with mean 50. i.6666. z = nificance. The heights of college students in a city are normally distributed with a S. z= x1 − x2 n1 s1 + n2 s2 2 2 n1 + n2 ⎛1 1⎞ ⎜n +n ⎟ ⎝ 1 2⎠ . What must be the minimum size of the sample? 5. H0 is rejected 4. of 6 cms.

there is significant difference between the average bonus incomes of the localities. Σ( x − x ) 2 = 24.D. z= x1 − x2 s s + n1 n2 2 1 2 2 H1 : x1 ≠ x2 = 210 − 220 102 122 + 100 150 = −7. For sample I. the significant value of z at 5% level of significance. There is no significant difference between the sample means. i.84.000. The difference is not significant.1428 ∴ z = 7. H0 is accepted.00. Conclusion..e. x1 = x2 . H1 : x1 ≠ x2 Under the null hypothesis z = x1 − x s s + n1 n2 2 1 2 2 = 75 − 73 82 102 + 60 100 = 1.D.. Test whether there is any significant difference between the average bonus incomes of the localities.3912. Discuss the significance of the difference of the sample means. Null hypothesis H0. s2 = 12. H0 is rejected.000. Σx = 49. of $12. The S. of $10 in a sample of 100 people of a city. Example 3. Conclusion. n2 = 150. Sol. the significant value of z at 5% level of significance. Σx = 70. The average bonus income of people was $210 with a S.. Under H0. As the calculated value of z > 1. x2 = 220. s1 = 10. Sol. n2 = 1.1428. H1 : x1 ≠ x2 To calculate sample variance s12 = 1 784000 Σ(X1 − X1 ) 2 = = 784 1000 n1 .96. Mean S. Example 2. x1 = 210. of bonus incomes of the people of the city was $11. H 0 : x1 = x2 . For sample II.500.500.e.e.. i. Here n1 = 100. there is no difference between the bonus incomes of the localities. Σ( x − x ) 2 = 7.96. As the calculated value of z < 1.D.e.000. Sol. For another sample of 150 people. there is no significant difference between mean scores.D. i. Null hypothesis. H 0 : x1 = x2 . Null hypothesis H0. Intelligence tests were given to two groups of boys and girls. There is no significant difference between mean scores. the average income was $220 with S.1248 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ ILLUSTRATIVE EXAMPLES Example 1. i. n1 = 1000. Size Girls 75 8 60 Boys 73 10 100 Examine if the difference between mean scores is significant.

x2 = 510. n2 = 250. Null hypothesis H0. A random sample of 200 towns in anystate gives the mean population per town at 485 with a S. x1 = 485. Conclusion.e. Another random sample of the same size from the same state gives the mean population per town at 510 with a S... z = x1 − x2 s s + n1 n2 2 1 2 2 = 181. Conclusion. there is significant difference between the mean values of the two samples. Under H0. 3.5 179 S.52.21.. the test statistic is given by z = 1 2 = = −5. Example 4. of items Group I 50 Group II 75 x1 = x2 .D.0 9 (3.47 < 1. H1 : x1 ≠ x2 Mean 181. H0 is rejected.52 2 502 402 s12 s2 + + 200 200 n1 n2 ∴ z = 5.96. Is the difference between the mean values given by the two samples statistically significant? Justify your answer.e.e. of 40..e. As z > the tabulated value of z at 5% level of significance H0 is rejected. the test statistic z= = 49 − 47 = 1.0 3. i. i. . s1 = 50.5 − 179. No. As the calculated value of z > 1. Example 5. x2 = 2 = = 47 1000 1500 n1 n2 x1 − x2 2 s12 s2 + n1 n2 x1 = Under the null hypothesis. Here n1 = 200. 784 1600 + 1000 1500 Conclusion. i. There is no significant difference between the mean values. of 50. x1 = x2 .75 TEST OF SIGNIFICANCE FOR DIFFERENCE OF MEANS OF TWO LARGE SAMPLES 1249 ________________________________________________________________________________________________________ 2 s2 = 1 1 (2400000) = 11600 Σ(X 2 − X 2 ) 2 = 1500 n2 70500 Σx1 49000 Σx = = 49. From the data given below.6 Sol. i.D. the significant value of z at 5% level of significance.2089. there is significant difference between the samples. H : x1 ≠ x2 (Two-tailed test) x −x 485 − 510 Under H0. there is no significant difference between the sample means.96. There is no significant difference between the samples.470. s2 = 40. As the calculated value of z = 1. compute the standard error of the difference of the two sample means and find out if the two means significantly differ at 5% level of significance.6) 2 + 50 75 = 4. the significant value of z at 5% level of significance. H0 is accepted.D. Null hypothesis H0. Sol.

Mean S. Two random samples of sizes 1000 and 2000 of farms gave an average yield of 2000 kg and 2050 kg respectively. The means of two large samples of 1000 and 2000 members are 168. the mean grade was 75 with a S.D. the sample standard deviations don’t differ significantly.D. No significant difference Highly significant 49.D. 8. 3. of $40.5 5. For A. the average weekly food expenditure is $220 with a S.4 1. Examine whether the difference is significant. 400 shoppers are chosen at random in supermarket A. 7.D. An examination was given to 50 students of college A and to 60 students of college B. Can the samples be regarded as drawn from the same population of standard deviation 6.55 inches with a S. A sample of heights of 6400 soldiers has a mean of 67.75 cms and 170 cms respectively.. 5. The number of accidents per day was studied for 144 days in town A and for 100 days in town B and the following information was obtained.D. Town A Town B 4. of 2.56 inches while another sample of heights of 1600 sailors has a mean of 68.D. Examine whether the two samples differ significantly in yield. of 2. and the statistic .25 cms? Answers 1. Highly significant Not significant ________________________________________________________________________________________________________ 21. Mean number of accidents S. A random sample of 200 measurements from a large population gave a mean value of 50 and a S.e. 50.D. Size Girls 70 10 70 Boys 75 11 100 2.D. 8. Is there any significant difference between the performance of the students of college A and those of college B? 7. Determine the 95% confidence interval for the mean of the population.2 1.D. of 7. of 9 and for B.584. Test at 1% level of significance whether the average food expenditures of the two groups are equal.52 inches. the mean grade was 79 with a S. of 9. In a survey of buying habits.1250 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ TEST YOUR KNOWLEDGE 1. i. 5. The variance of wheat farms in the country may be taken as 100 kg. of $45. Highly significant Highly significant Not significant 3.85 inches and a S.5 Is the difference between the mean accidents of the two towns statistically significant? 6. Intelligence tests on two groups of boys and girls gave the following results. Do the data indicate that the sailors are on the average taller than soldiers? 4. Their average weekly food expenditure is $250 with a S. 4.416 2.76 TEST OF SIGNIFICANCE FOR THE DIFFERENCE OF STANDARD DEVIATIONS If s1 and s2 are the standard deviations of two independent samples then under the null hypothesis H0 : σ 1 = σ 2 . For 500 shoppers chosen at supermarket B. 6.

H0 : σ 1 = σ 2 . where σ 1 and σ 2 are population standard deviations s1 − s2 2 s12 s2 + 2n1 2n2 2n2 . the sample S.56 since z < 1.25 + 2000 2400 Since z < 1. Alternative hypothesis: H1 = σ 1 ≠ σ 2 (two-tailed) ∴ The test statistic is given by z= s1 − s2 σ 12 2n1 + 2 σ2 = s1 − s2 s12 s2 + 2 2n1 2n2 2 (∵ σ 1 = s1 . . x1 = 67.50.08 = 1.58 − 2.25.0387 6.58.58) 2 (2. s1 = 2.96 we accept the null hypothesis at 5% level of significance.e.50) 2 + 1000 1200 = 1.50) × 2 ×1000 2 ×1200 = 0. H0 = μ1 = μ2 . x2 = 67.96 we accept the null hypothesis at 5% level of significance. Mean height (in inches) Standard deviation Number in samples Country A 67. i.50 (2.25 2.58 1000 Country B 67.e.58) (2. Alternative hypothesis: H1 : μ1 ≠ μ2 (two-tailed test) z= x1 − x2 2 s12 s2 + n1 n2 = 67. s2 = 2. σ 2 = s2 for large samples) 2n2 2 = 2.25 (2.42 2.76 TEST OF SIGNIFICANCE FOR THE DIFFERENCE OF STANDARD DEVIATIONS 1251 ________________________________________________________________________________________________________ z= s1 − s2 σ 12 2n1 + 2 σ2 .’s do not differ significantly.6564 6. (ii) We set up the null hypothesis.42.21. when population standard deviations are not known then z = ILLUSTRATIVE EXAMPLES Example 1... Since the sample sizes are large we can take σ 1 = s1 = 2. σ 2 = s2 = 2. Random samples drawn from two countries gave the following data relating to the heights of adult males.D.58.42 − 67.50. i. Given: n1 = 1000. sample means do not differ significantly. n2 = 1200.50 1200 (i) Is the difference between the means significant? (ii) Is the difference between the standard deviations significant? Sol. (i) Null Hypothesis.

’s do not differ significantly. z = 2.D. i..e. 75 < 1.1252 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Example 2.e. n2 = 81. The yield of wheat in a random sample of 1000 farms in a certain area has a S. = 10 S. sample means do not differ significantly.’s are significantly different.321 Difference significant at 5% level. (ii) whether the difference in the variability in yields is significant. the sample S.96 we accept the null hypothesis at 5% level of significance.77 TEST OF SIGNIFICANCE OF SMALL SAMPLES When the size of the sample is less than 30. z = 1. of 224 kg. Alternative hypothesis: H1 = μ1 ≠ μ2 (two-tailed) x −x 84 − 81 The test statistic is z = 1 2 = = 0. z = 4. Another random sample of 1000 farms gives a S. x1 = 84. Are the S. Alternative hypothesis: H1 = σ 1 ≠ σ 2 (two-tailed) s1 − s2 s1 − s2 The test statistic is z = = 2 2 2 σ1 σ 2 s12 s2 + + 2n1 2n2 2n1 2n2 (∵ σ 1 = s1 ..D.D. s2 = 12. = TEST YOUR KNOWLEDGE 1. An intelligence test of two groups of boys and girls gives the following results: Girls Boys mean = 84 mean = 81 S.’s significantly different? Answers 1.7526 ∴ z = 1.D.D.D. s1 = 10. Given: n1 = 121. x2 = 81. H0 = μ1 = μ2 . (b) We set up the null hypothesis H0 = σ 1 = σ 2 .851 The S.31 Difference not significant at 5% level 2. per plot Set of 40 plots 1258 lb 34 Set of 60 plots 1243 lb 28 2. of 192 kg. examine (i) whether the difference in the mean yield of the two sets of plots is significant.1859 2 (10) 2 (12) 2 s12 s2 + + 121 81 n1 n2 Since z < 1. then the sample is called a small sample. The mean yield of two sets of plots and their variability are as given. For such a sample it will not be possible for us to assume that the random sampling distribution of .7526 100 144 + 2 ×121 2 × 81 since z = 1. σ 2 = s2 for large samples) 10 − 12 = −1.D.D. i. = 12 N = 121 N = 81 (a) Is the difference in mean scores significant? (b) Is the difference between the standard deviations significant? Sol.96 we accept the null hypothesis at 5% level of significance. Mean yield per plot S. ________________________________________________________________________________________________________ 21. (a) Null hypothesis.

To test if the sample mean ( X ) differs significantly from the hypothetical value μ of the population mean. Critical value of t The critical value or significant value of t at level of significance α degrees of freedom γ for the two-tailed test is given by P ⎡ t > tγ (α ) ⎤ = α ⎣ ⎦ P ⎡ t > tγ (α ) ⎤ = 1 − α ⎣ ⎦ The significant value of t at level of significance α for a single-tailed test can be determined from those of the two-tailed test by referring to the values at 2α . The t-distribution has a different value for each degree of freedom and when the degrees of freedom are infinitely large.f. the t-distribution is equivalent to normal distribution and the probabilities shown in the normal distribution tables are applicable.79 TEST I: t-TEST OF SIGNIFICANCE OF THE MEAN OF A RANDOM SAMPLE To test whether the mean of a sample drawn from a normal population deviates significantly from a stated value when variance of the population is unknown.—degrees of freedom where s/ n s= The t-table Σ(X − X) 2 . where X is the mean of the sample t= s/ n 1 n s2 = ∑ (Xi − X)2 with degrees of freedom (n − 1).79 TEST I: t-TEST OF SIGNIFICANCE OF THE MEAN OF A RANDOM SAMPLE 1253 ________________________________________________________________________________________________________ a statistic is approximately normal and the values given by the sample data are sufficiently close to the population values and can be used in their place for the calculation of the standard error of the estimate. Application of t-distribution Some of the applications of t-distribution are given below: 1.f. we use the statistic X−μ . . To test the significance of observed partial and multiple correlation coefficients.) d. 21. x −μ t-statistic is defined as t = ∼ t(n – 1 d.78 STUDENT’S t-DISTRIBUTION This t-distribution is used when the sample size is ≤ 30 and the population standard deviation is unknown. i. n −1 The t-table given at the end is the probability integral of the t-distribution. t-TEST 21.21.e. To test the significance between two sample means. n −1 i =1 At a given level of significance α1 and degrees of freedom (n – 1). 2. We refer to t-table tα (two-tailed or one-tailed).. H0 : There is no significant difference between the sample mean x and the population mean μ . 3.

t > tα H0 is rejected. 53 ± (1. H0 : There is no significant difference between the sample mean and the hypothetical population mean. s/ n x − tα s n < μ < x + tα s / n 95% confidence limits (level of significance 5%) are X ± t 0. the calculated value of t is more than the table value. t = = = −4 n −1 15 3 3 / 16 t = 4.05 .753. Sol.602) = 51. X± . 99% confidence limits (level of significance 1%) are X ± t0. i.048.951. Can this sample be regarded as taken from the population having 56 as its mean? Obtain 95% and 99% confidence limits of the mean of the population. The sum of squares of the deviation from mean is 135. H1 : μ ≠ 56 (Two-tailed test) t: X−μ ∼ t (n − 1 d. μ = 56. n = 16.) s/ n Given: X = 53. Note.01s / n .706. X± s 3 t0.05 = 1. s = n − 1 S ⎥ ⎣ ⎦ Example 1.293 n 16 s 3 t0. H 0 : μ = 56. d . t0.05 = 1.725) = 51. Instead of calculating s. n −1 i =1 i =1 ILLUSTRATIVE EXAMPLES n 2⎤ ⎡ 2 2 2 ⎢ (n − 1) s = nS . Σ(X − X) 2 = 135 s= Σ(X − X)2 135 53 − 56 −3 × 4 = = 3. Since s 2 = 1 n 1 n ∑ (Xi − X)2 ∴ S2 = n ∑ (Xi − X)2 . Fiducial limits of population mean If tα is the table of t at level of significance α at (n – 1) degrees of freedom X−μ < tα for acceptance of H0. n 16 99% confidence limits of the population mean. 53 ± (2.05 s / n . Since t = 4 > t0. 95% confidence limits of the population mean.753.f.e. Hence the sample mean has not come from a population having 56 as its mean.01 . A random sample of size 16 has 53 as its mean. we calculate S for the sample. fv = 16 − 1 = 15. Conclusion.1254 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ If the calculated t value is such that t < tα the null hypothesis is accepted. 54.. The hypothesis is rejected. 54.

2 2 4. Example 4.2 0. i. Conclusion. μ = 4000 hrs.2 0.21.f . γ = 19 d.31 ∴ s = 5.64 3.05 = 2. t0.4 10 5.e.9 8 4.123 0. H0 : There is no significant difference between the sample mean and the population mean.e. I. The 9 items of a sample have the following values: 45. t = 2.129 s2 = n −1 ⎣ 20 − 1 ⎥ ⎦ X−μ 42 − 45 Applying the t-test t = = = −2. 53. A sample of 20 items has mean 42 units and S. Conclusion.e. 5 units.e.1 5 5.12 For γ = 9. 48.1 0.2 0. there is significant Σ(X − X)2 3. I. μ = 45 units μ ≠ 45 (Two-tailed test) H1 : n = 20. the sample could not have come from this population. Test the hypothesis that it is a random sample from a normal population with mean 45 units.615 s / n 5.09 5.589. X−μ ∼ t (10 − 1 d.2 1. Example 3.6 1.04 X= s= 3. 47. H0 : There is no significant difference in the sample mean and population mean.. 50. 51.615.09. is t0.5 0.6 Can we accept the hypothesis that the average lifetime of a bulb is 4000 hrs? Sol.129 / 20 The tabulated value of t at 5% level for 19 d.e.. The lifetime of electric bulbs for a random sample of 10 from a large shipment gave the following data: Item Life in 1000s of hrs. the hypothesis H0 is rejected.589 n −1 9 10 difference between the sample mean and the population mean.3 – 0. 49.2 – 0.12 4. I. Since t > t0.8 0.6 0.4 − 4 = = 0.) Applying the t-test: t = s/ n X X−X (X – X )2 4.25 4.01 4. the average lifetime of the bulbs could be 4000 hrs.5? .8 7 3.f.05.6 3 3. X = 42. Does the mean of these values differ significantly from the assumed mean 47.D. ∴ The hypothesis μ = 4000 hrs is accepted.. S = 5.9 – 0.05. Given : n 2 ⎡ 20 ⎤ 2 S =⎢ (5) = 26..26. i.25 4.. 52. Sol.f.9 – 0.4 0 0 5. t = = 2.36 3.6 0.9 4 4.3 9 4.04 4.5 0.1 – 0.44 ΣX 44 = = 4.4 n 10 Σ(X − X) 2 = 3. 1 4.79 TEST I: t-TEST OF SIGNIFICANCE OF THE MEAN OF A RANDOM SAMPLE 1255 ________________________________________________________________________________________________________ Example 2.8 – 0. 47. Since the calculated value of t is less than table t0.3 0.05 = 2.2 6 3.

9 3.05 X − μ 49. 83.1 4. 66.619 n 9 (n − 1) Applying the t-test t= t0.05.5 (1.41 49 – 0.6) 8 = = = 1. i. Could the sample come from a population having a mean of 500 gm? Sol. Since t < t0. 45.333 > t0. TEST YOUR KNOWLEDGE 1.7279 2. Test whether the mean length of the shipment can be taken as 46.01 53 3. s = = 6. 70. 4. 88. 46.81 52 2. A sample of 18 items has a mean of 24 units and a standard deviation of 3 units.Q. X = 490. H1: μ ≠ 500 Applying t-test t= t0. Ten individuals are chosen at random from a normal population of students and their grades are found to be 63.1 4.41 50 0.05.61 (X – X )2 16. The following values give the lengths of 12 samples of Egyptian cotton taken from a shipment: 48..1 47 – 2. 98. Given: n = 10. Since t = . given : n = 9. S. and 100. 3.9 15.11.e.D.5 (two-tailed test). 43. S = 9 gm. 101. In light of these data..e. 2.9 8.41 48 – 1. 49. μ = 47.486 9 n −1 X−μ 490 − 500 = = −0. 63. there is no significant difference between their mean. μ = 500 s= n 2 10 2 S = × 9 = 9. 45.5 I. 110.31 for γ = 8. 71.1256 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Sol.619 / 8 = 2..’s 70. The following results are obtained from a sample of 10 boxes of biscuits.86 ∴ s = 2. H0 : The difference is not significant.619 s / n 2. i. 69. 107. 52. Mean weight content = 490 gm. 67. 46. μ ≠ 500. of the weight 9 gm.26 for γ = 9. 95. Σ(X − X) = 54.e.05 Conclusion.e. 70. of 160? . Do these data support the assumption of a population mean I. 68.1 0. the hypothesis is accepted. Test the hypothesis that it is a random sample from a normal population with a mean of 27 units.5 X X−X 45 – 4.1 1. i. Conclusion. Example 5.486 / 10 = 2.9 0.21 47 – 2. 47. 50.. A random sample of 10 students had the following I.89. ∴ The sample could not have come from the population having mean 500 gm.1 − 47. 120. H0 : μ = 47.Q. μ = 500. the hypothesis H0 is rejected. 46. discuss the suggestion that the mean grade of the population of students is 66.21 51 1.81 Σx 442 Σ(X − X) 2 2 2 X= = = 49. there is no significant difference between the sample and the population mean. 71.333 s / n 9. H1 : μ ≠ 47. 47.

Let X.6. 5. s/ n The test statistic is t = I.80 TEST II: t-TEST FOR DIFFERENCE OF MEANS OF TWO SMALL SAMPLES (FROM A NORMAL POPULATION) This test is used to test whether the two samples of sizes x1. 4. . . t = X−Y s1 + s2 2 2 n1 s1 + n2 s2 2 2 n1 + n2 − 2 . yn2 of sizes n1. 5.. yi ) are the paired data i = 1. i.1.6. n2 have been drawn from two normal populations with mean μ1 and μ2 respectively under the assumption that the population variances are equal. where ( xi . . 5. 4. Two samples of sodium vapor bulbs were tested for length of life and the following results were returned: Type I Type II Size 8 7 Sample mean 1234 hrs 1036 hrs Sample S. If the pairs of values are in some way associated (correlated) we can’t use the test statistic as given in Note 2.0.2. H0 : μ1 ≠ μ2 . If n1 = n2 = n. If the two sample standard deviations s1. . Y be the means of the two samples.4. can be used as a test statistic. .f. accepted accepted 3. X−μ t= with degrees of freedom n – 1. d s/ n or t = d s/ n −1 . Under this H0 the test of statistic t is given by t = (X − Y) ∼ t (n1 + n2 − 2 d.. A sample of 10 bags gave the following weights: 4. i. and 4. (σ 1 = σ 2 = σ ). accepted accepted 2.e. Answers 1. where d is the mean of paired difference. . 2. H0 : The samples have been drawn from the normal population with means μ1 and μ2 . 5. xn1 .e.D.9. . n. 4.e. . ILLUSTRATIVE EXAMPLES Example 1. .21.7.80 TEST II: t-TEST FOR DIFFERENCE OF MEANS OF TWO SMALL SAMPLES 1257 ________________________________________________________________________________________________________ 5. rejected ________________________________________________________________________________________________________ 21. In this case we find the differences of the associated pairs of values and apply for a single mean.) 1 1 s + n1 n2 2 Note 1. y2. 4. 36 hrs 40 hrs Is the difference in the means significant enough to generalize that type I is superior to type II regarding length of life? . s2 are given then we have s = Note 2. d i = xi − yi d i = X − Y. 5. A filling machine is expected to fill 5 kg of powder into bags. .1. 5. .7. y1. x2. Test whether the machine is working properly.. n −1 Note 3. .

5 and 5.7317 8+7−2 n1 + n2 − 2 X1 − X 2 1234 − 1036 = = 18. s1 = 3. type I is superior to type II s2 = The t-statistic t= 2 2 n1s2 + n2 s2 8 × (36) 2 + 7(40) 2 = = 1659.2) 2 = = 22. Example 2.775 ∴ s = 4. H0 : μ1 = μ2 . the means of the two populations are the same. Samples of sizes 10 and 14 were taken from two normal populations with S.076 ∴ s = 40..05. 13 is 1. Example 3.f.8604 1 1 ⎛ 1 1 ⎞ s + + ⎟ 4. H0 : μ1 = μ2 .3 and 18.6. i..0739.772 ⎜ n1 n2 ⎝ 10 14 ⎠ The value of t at 5% level for 22 d.3 − 18. s2 = 5..f. 62... 66. 69. i.8604 < t0. i. Since calculated t > t0. 68. Test whether the means of the two populations are the same at 5% level.3. 71.6 = = 0.1480 ∼ t (n1 + n2 − 2 d.e. i. and 73.5) 2 + 14(5.e. Given X1 = 20. H0 : μ1 = μ2 . Let X1 and X2 be the two samples denoting the heights of sailors and soldiers.e. Sol. Conclusion. 69.2. 65. s2 = ⎦ n1 + n2 − 2 ⎣ i = 1 ni j = 1 n2 is an unbiased estimate of the population variance σ 2 . 3. 70.772 10 + 14 − 2 n1 + n2 − 2 X1 − X 2 20.e. 72. I.f.2 s2 = t= 2 n1s12 + n2 s2 10(3. t follows t distribution with n1 + n2 – 2 degrees of freedom. The sample means were found to be 20. taller than the soldiers.e.05 at d. The heights of 6 randomly chosen sailors in inches are 63. Sol. n2 = 14.D.05 = 2. Given the sample size n1 = 6. H1 : μ1 ≠ μ2 . 65. X 2 = 18. H1 : μ1 > μ2 (one-tailed test) . n1 = 10.) 1 1 1 1 s 40. two types of bulbs have the same lifetime.. H0 is rejected. H1 : μ1 > μ2 . Those of 9 randomly chosen soldiers are 61.6. Test whether the sailors are.5. H1 is accepted.7317 + + n1 n2 8 7 t0.1258 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Sol. ∴ Type I is definitely superior to type II n1 n2 Y X 1 ⎡Σ(X i − X) 2 + (Y j − Y) 2 ⎤ Y=∑ j. i.77 (one-tailed test) Conclusion. the means of both the population are the same.e. where X = ∑ i . on the average. there is no significant difference between their means. is t0. 71. Since t = 0. and 72.05 the hypothesis is accepted. n2 = 9.

Σ(X 2 − X 2 ) 2 = 152.e.66. 4.035 X2 = s2 = = 7. 5.3031 ∼ t (n1 + n2 − 2 d.0382 + s + n1 n2 6 9 The value of t at 10% level of significance (∵ the test is one tailed) for 13 d. taller than the soldiers.5156 ΣX 2 = 67. H1 : μ1 > 0 The test statistic under H0 t= d ∼ t (n − 1 degrees of freedom) s / n −1 5 + 2 + 8 + (−1) + 3 + 0 + 6 + (−2) + 1 + 5 + 0 + 4 d= = 2.038 6+9−2 X − X2 68 − 67. 0.21.34 70 2. there is no significant difference between their average.f.66 69 1.583 12 . I.77. is 1.66 44.f.. σ .e. Example 4. 2. 8.34 71 3. I. H0 : μ = 0.0756 2.34 73 5. 6. we have to assume that this population is normal with mean μ and S.3031 < t0. 1 [60 + 152. Conclusion. Since t = 0. on the average.36 63 –5 25 65 –3 9 68 0 0 69 1 1 71 3 9 72 4 16 ΣX1 = 68. the sailors are not.0002 n2 1 ⎡ Σ(X1 − X1 )2 + Σ(X 2 − X 2 ) 2 ⎤ ⎦ n1 + n2 − 2 ⎣ Under H0.66 66 1. 1.34 62 – 5.77 the hypothesis H0 is accepted. Can it be concluded that the stimulus will in general be accompanied by an increase in blood pressure? Sol. To test whether the mean increase in blood pressure of all patients to whom the stimulus is administered will be positive.8356 28.34 72 4.4756 11.) 1 1 1 1 4. –2.3077 ∴ s = 4.. 3.7956 5.66 32. Σ(X1 − X1 ) 2 = 60 n1 65 – 2.80 TEST II: t-TEST FOR DIFFERENCE OF MEANS OF TWO SMALL SAMPLES 1259 ________________________________________________________________________________________________________ Calculation of two sample means: X1 X1 − X1 (X1 – X 1 )2 X1 = X2 X2 − X2 (X2 – X 2 )2 61 – 6.666 t= 1 = = 0.0002] = 16.7556 1.05 = 1. A certain stimulus administered to each of 12 patients resulted in the following increases of blood pressure: 5.D. which are unknown. –1.1556 18. 0.

. Example 5.f.2.31.744 ∴ s = 2.583 11 d = = = 2.359 1.7778 × 8 t= = = = −1.583 2. ∵ t > t0. s 2 = − (d ) 2 = − (−0. we use the paired t-test.9571/ 12 − 1 t= Conclusion.1260 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ s2 = 1 Σd 2 − d 2 = [52 + 22 + 82 + (−1) 2 + 32 + 02 + 62 n 12 + (−2) 2 + 12 + 52 + 02 + 42 ] − (2.f.897 ∼ t (n − 1 d.f. Since the data are correlated and concerned with the same set of students. the stimulus does not increase the blood pressure.9571 s / n − 1 2. The tabulated value of t0.e. State whether the course was effective or not from the data below (in the same units).6172 / 8 s / n −1 The tabulated value of t0.05 at 11 d.9571 2. Before medication (X) 10 15 9 3 7 12 16 17 4 After medication (Y) 12 17 8 5 6 11 18 20 3 d=X–Y –2 –2 1 –2 1 1 –2 –3 1 Σd = −7 d2 4 4 1 4 1 1 4 9 1 Σd 2 = 29 d= 29 Σd −7 Σd 2 = = −0. Before After 10 12 15 17 9 8 3 5 7 6 12 11 16 18 17 20 4 3 Sol.583) 2 = 8.7778) 2 = 2.6177 2. I. is 2. . H0 : Medication was not effective μ1 = μ2 H1 : μ1 ≠ μ2 (Two-tailed test).7778.05 at 8 d. is 2. The stimulus in general will be accompanied by an increase in blood pressure.) 2. H0 is rejected.05.617 n 9 n 9 d −0. The memory capacity of 9 students was tested before and after a course of medication for a month.7778 −0.

7666 ∼ t (n1 + n2 − 2 d.4 11.. The following figures refer to observations in live independent samples.875 + n1 n2 10 10 t = 0.76 20 – 9.7 114..4 54. i.49 30 0.29 10 34 7.05.89 151.e. Example 6.7 0.29 X1 = ∑ X1 = 26. i. there is no significant difference between their means. .3 10 i = 1 n2 Σ(X1 − X1 ) 2 = 486.80 TEST II: t-TEST FOR DIFFERENCE OF MEANS OF TWO SMALL SAMPLES 1261 ________________________________________________________________________________________________________ Conclusion.08] = 62.4 s2 = = Σ(X 2 − X 2 ) 2 = 630.6 2.3 53.4 1.76 31 1.e.21.3 86.7 30 3.026 ∴ s = 7.08 1 ⎡Σ(X1 − X1 ) 2 + Σ(X 2 − X 2 ) 2 ⎤ ⎦ n1 + n2 − 2 ⎣ 1 [486.6 13 – 13. medication was not effective in improving performance.4 43.7666.49 23 – 6.49 22.4 + 630. i.359 < t0.96 36 6.e.67 21.56 34 4.09 44.4 22 4.3 39.6 38 11.875 10 + 10 − 2 Under H0 the test statistic is given by t= X1 − X 2 26.96 22 –7..56 184.7 28 1. let X1 be the sample I and X2 be the sample II.7 2.) 1 1 1 1 s + 7. H0 is accepted.49 24 – 2. Since t = 1.6 i = 1 n1 X2 = ∑ X 2 293 = = 29.6 6.3 = = −0.96 29.89 10 20 – 6.7 17 – 12.f. Sample I Sample II 25 40 30 34 28 22 34 20 24 31 20 40 13 30 32 23 22 36 38 17 Analyze whether the samples have been drawn from the populations of equal means. Sol.6 32 5.56 40 10.3 ( X 2 − X 2 ) 2 114. μ1 = μ2 H1 : μ1 ≠ μ2 (Two-tailed test) Given n1 = Sample I size = 10.6 − 29. n2 = Sample II size = 10 To calculate the two sample means and the sum of squares of deviation from the mean. H0 : The two samples have been drawn from the population of equal means.16 40 10.16 129. X1 X1 − X1 ( X1 − X1 )2 X2 X2 − X2 25 – 1.

is 2. Diet A : 5 6 8 1 12 4 3 9 6 10 Diet B : 2 3 6 8 10 1 2 8 Does it show the superiority of diet A over diet B? 4.e. The prices were noted below: City 1 : 61 63 56 63 56 63 59 56 44 61 City 2 : 55 54 47 59 51 61 57 54 64 58 Test whether the average prices can be said to be the same in the two cities. 3. A group of 10 boys fed on diet A and another group of 8 boys fed on a different diet B. : $25 Find whether the average sales differ significantly. 6. A second sample of 17 motors chosen from a different batch showed a mean life of 1280 hrs with a S. of 398 hrs. accepted rejected 4. of 423 hrs. H0 is accepted.D. rejected rejected 3.05. 6. 7.7666 < t0. Two salesmen represent a firm in a certain company. 10 shops were visited at random in each town. A sample survey was made and the following results were obtained: No. accepted accepted 2. One of them claims that he makes larger sales than the other. TEST YOUR KNOWLEDGE 1. we assumed that the two samples came from the same population or a population with equal variance.. To compare the prices of a certain product in two cities.1262 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Conclusion. they recorded the following increase in weight (kgs).e. The average number of articles produced by two machines per day are 200 and 250 with standard deviation 20 and 25 respectively on the basis of records of 25 days’ production. 5.81 SNEDECOR’S VARIANCE RATIO TEST OR F-TEST In testing the significance of the difference of two means of two samples. 2nd Salesman (20) $175 $20 Answers 1.f. accepted ________________________________________________________________________________________________________ 21. I. 5. The mean life of 10 electric motors was found to be 1450 hrs with a S. Since the calculated value t = 0. Is there a significant difference between the means of the two samples? 2.. Can you regard both the machines as equally efficient at 5% level of significance? 7. Two independent samples of sizes 7 and 9 have the following values: Sample A : 10 12 10 13 14 11 10 Sample B : 10 13 15 12 10 14 11 12 11 Test whether the difference between the means is significant. The grades obtained by a group of 9 regular course students and another group of 11 part-time course students in a test are given below Regular : 56 62 63 54 60 51 67 69 58 Part-time : 62 70 71 62 60 56 75 64 72 68 66 Examine whether the grades obtained by regular students and part-time students differ significantly at 5% and 1% levels of significance.1. I.D. The . The tabulated value of t at 5% level of significance for 18 d. the two samples have been drawn from the populations of equal means. of sales : 1st Salesman (18) Average sales : $210 S.D. there is no significant difference between their means.

05 for (n1 – 1). s12 Under H0 : F = 2 ∼ F(v1 . the numerator is greater than the denominator (Dr). i. σ 12 = σ 2 = σ 2 .. (ii) Whether the two independent estimates of the population variance are homogeneous or not. To carry out the test of significance of the difference of the variances we calculate the test s2 2 statistic (Nr) F = 12 . 2.e.) s2 . If the calculated value of F exceeds F0. v2 = n2 − 1. That is why we take the larger variance in the numerator of the ratio. The ratio of σ 12 to σ 2 should be equal to 1 or greater than 1. The estimates of the population variance based on these samples are s12 = freedom of these estimates are v1 = n1 − 1. The samples must be random and independent.f. The assumptions on which the F-test is based are: n s2 n1s12 2 and s2 = 2 2 . we set up the null hypothesis H0 : σ 12 = σ 2 = σ 2 . s12 > s2 . the independent estimates of the common population do not differ significantly. Hence before applying the t-test for the significance of the difference of two means. there is no significant difference between population variance.e.4 and 102. Null hypothesis H0. s2 Conclusion. 2 To test whether these estimates s12 and s2 are significantly different or whether the samples may be regarded as drawn from the same population or from two populations with the same 2 variance σ 2 . The populations for each sample must be normally distributed. (n2 – 1) degrees of freedom given in the table we conclude that the ratio is significant at 5% level. i.6.. I. In two independent samples of sizes 8 and 10 the sum of squares of deviations of the sample values from the respective sample means were 84. we have to test for the equality of population variance by using the F-test. Test whether the difference of variances of the populations is significant or not.e. ILLUSTRATIVE EXAMPLES Example 1. v2 d.81 SNEDECOR’S VARIANCE RATIO TEST OR F-TEST 1263 ________________________________________________________________________________________________________ object of the F-test is to discover whether two independent estimates of population variance differ significantly or whether the two samples may be regarded as drawn from the normal populations having the same variance. 2 3. we conclude that the sample could have come from two normal populations with the same variance.e. I. 2 Sol.. 2 Let n1 and n2 be the sizes of two samples with variance s12 and s2 . Applications. The F-test is used to test (i) whether two independent samples have been drawn from the normal populations with the same variance σ 2 . The degrees of n2 − 1 n1 − 1 1.21..

2 s2 11.286 ( X 2 − X 2 )2 7.625 5.286 6.4 n1 − 1 7 n2 − 1 9 s12 12.625 3.29 and F = 1. Two random samples are drawn from two normal populations as follows: A B 17 16 27 16 18 20 25 27 27 26 29 25 13 21 17 Test whether the samples are drawn from the same normal population.29 = F0.657 53.365 7.89 54.6 s12 = F= Σ(X1 − X1 ) 2 84. n1 = Sample I size = 8. σ 12 = σ 2 .05 = 3..14 11.057.286 8.e.286 7. ∴ There is no significant difference between the variance of the populations.4 Conclusion. (if s12 > s2 ) 2 s2 2 2 Computations for s1 and s2 X1 17 27 18 25 27 29 13 17 X1 − X1 – 4.39 X2 16 16 20 27 26 25 21 X2 − X2 – 2.735 – 8.4 Σ(X 2 − X 2 ) 2 102. Null hypothesis H0.735 7. the population variances do not differ significantly.653 68. Since the t-test assumes that the sample variances are equal.714 – 2. 2 Alternative hypothesis. The tabulated value of F at 5% level of significance for (7.0576.39 74.365 1. 9) d.39 28.0576 > 3. i.057 2 ∵ s12 > s2 ∴ F = = 1. is 3.625 ( X1 − X1 )2 21.513 5. we shall first apply the F-test.4. Σ(X 2 − X 2 ) 2 = 102.89 13. v2 = n2 – 1. H1 : σ 12 ≠ σ 2 Test statistic: F = s12 2 .286 2. Example 2.714 1.1264 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ where v1 = n1 – 1. 2 F-test.085 39.735 – 3. s2 = = = 11.39 21.f.226 .625 – 4.375 5. n2 = Sample II size = 10 Σ(X1 − X1 ) 2 = 84.05 ⇒ H0 is accepted. Sol.39 28. To test whether two independent samples have been drawn from the same population we have to test (i) equality of the means by applying the t-test and (ii) equality of the population variance by applying the F-test.6 2 = = 12.29 ∴ F0.

∴ We conclude that the two samples have been drawn from the same normal population.87 = = 36.81 SNEDECOR’S VARIANCE RATIO TEST OR F-TEST 1265 ________________________________________________________________________________________________________ X1 = 21.267.190.47 F= Conclusion.859 = = 30.16. i.267 = = 1.796 + s + 8 7 n1 n2 Conclusion. i.e..796 8+7−2 n1 + n2 − 2 X1 − X 2 21. μ1 = μ2 . Σ(X1 − X1 ) 2 = 253.f.. σ 12 = σ 2 . Hence we conclude that the variability in two populations is the same. n2 = 7. 1 1 1 1 5. Σ(X 2 − X 2 ) 2 = 182.87 X 2 = 18. Example 3..714 = = 0. 7 n1 − 1 Σ(X 2 − X 2 ) 2 182.. H0 : The variances are equal. Alternative hypothesis.859 = = 33. The table value of F for v1 = 7 and v2 = 6 degrees of freedom at 5% level is 4.859 s12 = 2 s2 = Σ(X1 − X1 ) 2 253.47 n2 − 1 6 s12 36. H0 is accepted. s2 . H1 : μ1 ≠ μ2 Test of statistic s2 = t= Σ(X1 − X1 ) 2 + Σ(X 2 − X 2 ) 2 253.594 ∴ s = 5. 2 Sol. i. The tabulated value of t at 5% level of significance for 13 d. n1 = 8. The calculated value of t is less than the tabulated value.87 + 182.f.625 − 18.. H0 : μ1 = μ2 . ∴ H0 is accepted.e.714.625. 2 H1 : σ 12 ≠ σ 2 s12 2 2 Under the null hypothesis.21. 2 s2 30.e.e.e. the population means are equal. i. the samples have been drawn from normal populations with the same variance. t-test: Null hypothesis. there is no significant difference between the population mean. is 2. I.21. Two independent samples of sizes 7 and 6 had the following values: Sample A Sample B 28 29 30 30 32 30 33 24 31 27 29 28 34 Examine whether the samples have been drawn from normal populations having the same variance.9704 ∼ t (n1 + n2 − 2) d. The calculated value of F is less than the tabulated value of F. the test statistic F = 2 ( s1 > s2 ).

1266 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________
2 2 Computations for s1 and s2

X1 28 30 32 33 31 29 34

X1 − X1 –3 –1 1 2 0 –2 3

( X1 − X1 )2 9 1 1 4 0 4 9 28

X2 29 30 30 24 27 28

X2 − X2 1 2 2 –4 –1 0

( X 2 − X 2 )2 1 4 4 16 1 0 26

X1 = 31, n1 = 7; Σ(X1 − X1 ) 2 = 28 X 2 = 28, n2 = 6; Σ(X 2 − X 2 ) 2 = 26 Σ(X1 − X1 ) 2 28 Σ(X 2 − X 2 ) 2 26 2 s = = = 4.666; s2 = = = 5.2 n1 − 1 6 n2 − 1 5
2 1

F=

s12 5.2 = = 1.1158. 2 s2 4.666

2 (∵ s2 > s12 )

Conclusion. The tabulated value of F at v1 = 6 – 1 and v2 = 7 – 1 d.f. for 5% level of significance is 4.39. Since the tabulated value of F is less than the calculated value, H0 is accepted, i.e., there is no significant difference between the variances, i.e., the samples have been drawn from the normal population with the same variance. Example 4. The two random samples reveal the following data:

Sample no. I II

Size 16 25

Mean 440 460

Variance 40 42

Test whether the samples come from the same normal population. Sol. A normal population has two parameters, namely, the mean μ and the variance σ 2 . To test whether the two independent samples have been drawn from the same normal population, we have to test (i) the equality of means (ii) the equality of variance. Since the t-test assumes that the sample variances are equal, we first apply the F-test. 2 F-test. Null hypothesis. σ 12 = σ 2 The population variances do not differ significantly. 2 Alternative hypothesis. σ 12 ≠ σ 2 Under the null hypothesis the test statistic is given by F = s12 2 2 , ( s1 > s2 ) 2 s2

21.81 SNEDECOR’S VARIANCE RATIO TEST OR F-TEST 1267 ________________________________________________________________________________________________________
2 Given, n1 = 16, n2 = 25; s12 = 40, s2 = 42

n1s12 s12 n1 − 1 16 × 40 24 = × = 0.9752. ∴ F= 2 = 2 n2 s2 s2 15 25 × 42 n2 − 1 Conclusion. The calculated value of F is 0.9752. The tabulated value of F at 16 – 1, 25 – 1 d.f. for 5% level of significance is 2.11. Since the calculated value is less than that of the tabulated value, H0 is accepted, i.e., the population variances are equal. t-test. Null hypothesis. H0 : μ1 = μ2 , i.e., the population means are equal. Alternative hypothesis. H1 : μ1 ≠ μ2 under the null hypothesis the test statistic: Given: n1 = 16, n2 = 25, X1 = 440, X 2 = 460
s2 = t=
2 n1s12 + n2 s2 16 × 40 + 25 × 42 = = 43.333 ∴ s = 6.582 16 + 25 − 2 n1 + n2 − 2

X1 − X 2 440 − 460 = = −9.490 for (n1 + n2 − 2) d.f. 1 1 1 1 6.582 s + + 16 25 n1 n2

Conclusion. The calculated value of t is 9.490. The tabulated value of t at 39 d.f. for 5% level of significance is 1.96. Since the calculated value is greater than the tabulated value, H0 is rejected. I.e., there is a significant difference between the means, i.e., μ1 ≠ μ2 . Since there is a significant difference between the means, and no significant difference between the variances, we conclude that the samples do not come from the same normal population. Example 5. Two random samples drawn from two normal populations have the variable values as below:

Sample I Sample II

19 28

17 32

16 40

28 37

22 30

23 35

19 40

24 28

26 41 45 30 36

Obtain the estimate of the variance of the population and test whether the two populations have the same variance. ΣX1 ΣX 2 Sol. X1 = = 21.55; n1 = 9; X 2 = = 35.166; n2 = 12 n1 n2 X1 19 17 16 28 d1 = X 1 − 17 2 0 –1 11 d12 4 0 1 121 X2 28 32 40 37 d 2 = X 2 − 28 0 4 12 9
2 d2

0 16 144 81 (continued)

1268 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________

22 23 19 24 26

5 6 2 7 9

25 36 4 49 81

30 35 40 28 41 45 30 36

2 7 12 0 13 17 2 8

4 49 144 0 169 289 4 64 Σd 22 = 964

Σd12 = 321 s12 =
2 s2 =

Σ(X1 − X1 ) 2 Σd12 − n1 (X1 − A) 2 321 − 9(21.55 − 17) 2 = = = 16.834 n1 − 1 n1 − 1 9 −1 Σ(X 2 − X 2 ) 2 Σd 22 − n2 (X 2 − A) 2 964 − 12(35.166 − 28) 2 = = = 31.616 12 − 1 n2 − 1 n2 − 1
2 (∵ s2 > s12 )

2 s2 31.616 = 1.878. F= 2 = s1 16.834

Conclusion. The calculated value of F is 1.878. The tabulated value of F for v2 = 12 – 1 = 11, v1 = 9 – 1 = 8 d.f. at 5% level of significance is 3.315. Since the calculated value of F is

less than the tabulated value, H0 is accepted, i.e., there is no significant difference between the population variance, i.e., the two populations have the same variance.
TEST YOUR KNOWLEDGE
1. From the following two sample values find out whether they have come from the same population:

Sample 1 Sample 2

17 16

27 16

18 20

25 16

27 20

29 17

27 15

23 21

17

2. The daily wages in dollars of skilled workers in two cities are as follows:

Size of sample of workers City A City B

S.D. of wages in the sample

160 130

250 320

3. The standard deviation calculated from two random samples of sizes 9 and 13 are 2.1 and 1.8 respectively. May the samples be regarded as drawn from normal populations with the same standard deviation?

these results are rarely achieved. the observed and expected frequencies completely coincide. . 2. though we are to choose any four numbers. 2. In general. rejected 2. then χ 2 is defined as n ⎡ (O − E i ) 2 ⎤ χ2 = ∑⎢ i ⎥ Ei i =1 ⎣ ⎦ where ΣOi = ΣE i = N (total frequency) and degrees of freedom (d. . . the theoretical considerations lead us to expect 100 heads and 100 tails. There is only one restraint on our freedom and our degrees of freedom are 4 – 1 = 3.) = (n – 1). Note. accepted ________________________________________________________________________________________________________ 21.21.) are usually denoted by ν (the letter nu of the Greek alphabet). Note. . ν = ( p – 1) (q – 1) (ii) In the case of a contingency table. ν = n – k. The greater the discrepancy between the observed and expected frequencies. the greater the value of χ2. If we have to choose any four numbers whose sum is 50. Thus.82 CHI-SQUARE (χ2) TEST 1269 ________________________________________________________________________________________________________ 4. the observed and theoretical frequencies agree exactly. n) is a set of observed (experimental) frequencies and Ei (i = 1. If two restrictions are imposed. .f. If χ = 0. where k is the number of independent constraints in a set of data of n observations. our freedom to choose will be further curtailed and the degrees of freedom will be 4 – 2 = 2. Thus χ2 affords a measure of the correspondence between theory and observation.82 CHI-SQUARE ( χ2 ) TEST When a coin is tossed 200 times. 2 (ii) If χ > 0 they do not agree exactly. . Thus. (i) If χ = 0. But in practice. The quantity χ2 (the Greek letter chi squared. our choice is reduced to three because of an imposed condition.f. n) is the corresponding set of expected (theoretical or hypothetical) frequencies.82.1 Degrees of Freedom While comparing the calculated value of χ2 with the table value. . Two independent samples of size 8 and 9 had the following values of the variables: Sample I Sample II 20 30 30 31 23 32 25 34 21 35 22 29 23 28 24 27 26 Do the estimates of the population variance differ significantly? Answers 1. we can exercise our independent choice for any three numbers only. we have to determine the degrees of freedom. pronounced chi-square) describes the magnitude of discrepancy between theory and observation. accepted 3. 2 21. accepted 4. (i) For a p × q contingency table ( p columns and q rows). . the number of degrees of freedom is the total number of observations less the number of independent constraints imposed on the observations. the expected frequency of any class Total of row in which it occurs × Total of columns in which it occurs = Total number of observations . the fourth being 50 minus the total of the three numbers selected. Degrees of freedom (d. If Oi (i = 1.

In general. If the data is given in a series of “n” numbers then degrees of freedom = n – 1. the degrees of freedom are 2 less than the number of classes. or Normal. Poisson.f.71828.f. because we use the total frequency and the arithmetic mean to get the parameter of the Poisson distribution. the sampling distribution of χ2 can be closely approximated by a continuous curve known as the chi-square distribution. It is important to remember that the number of degrees of freedom is determined with the number of classes after regrouping. If small theoretical frequencies occur (i.1270 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ The χ2 test is one of the simplest and the most general tests known.82. c = a constant depending only on ν .. When we fit a normal curve. Here again. should be linear.e. etc. fit empirical distributions. (ii) as a test of independence of attributes. In the case of Poisson distribution d.82. = n – 2. < 10). which is usually known as “Yates’s correction for continuity.f. = n – 3. i. 21. should be large. we may say that N should be at least 50. however few the cells. mean. (c) The constraints on the cell frequencies.5 to the cell frequency that is less than 5 and adjust the remaining cell frequency suitably so that the marginal total is not changed. = n – 1. the number of degrees of freedom are 3 less than the number of classes. Symbolically. In the case of Binomial distribution d. which can be summed up under the following heads: (i) as a test of goodness of fit. In the case of Normal distribution d.2 Conditions for Applying the χ2 Test Following are the conditions that should be satisfied before the χ 2 test can be applied. the difficulty is overcome by grouping two or more classes together before calculating (O – E). ν = number of degrees of freedom. The probability function of χ2 distribution is given by f ( χ 2 ) = c( χ 2 )(ν /2−1) e − x 2 /2 where e = 2. but as an arbitrary figure. where k refers to the number of independent constraints. when we fit a Poisson distribution.4 The χ2 Test as a Test of Goodness of Fit The χ2 test enables us to ascertain how well the theoretical distributions such as Binomial. Yates. and are obtained by the rule ν = n – k. . If any one of the theoretical frequencies is less than 5.. 21. 21. (iv) as a test of the hypothetical value of the population variance σ 2 . the total number of frequencies. we then apply a correction given by F. because in this fitting we use the total frequency. the degrees of freedom are denoted by the symbol ν or by d. and standard deviation. (b) No theoretical cell-frequency should be small.82.3 The χ2 Distribution For large sample sizes. but 5 should be regarded as the very minimum and 10 is better. Note. if any.” we add 0.e. distributions obtained from sample data. (v) as a list of the homogeneity of independent estimates of the population correlation coefficient. (a) N. (iii) as a test of homogeneity of independent estimates of the population variance. It is difficult to say what constitutes largeness.f. It is applicable to a very large number of problems in practice. it is difficult to say what constitutes smallness. when we fit a binomial distribution the number of degrees of freedom is one less than the number of classes.

6 14 14 0 14 14 0 18 14 16 12 14 4 11 14 9 15 14 1 Σ(Oi − E i ) 2 30 = = 2. Under this H0.) is 11. of accidents Mon 14 Tue 18 Wed 12 Thu 11 Fri 15 Sat 14 Sol. Since the calculated value of χ2 is less than the tabulated value. Example 2. Under this H0.82 CHI-SQUARE (χ2) TEST 1271 ________________________________________________________________________________________________________ If the calculated value of χ2 is less than the table value at a specified level (generally 5%) of significance. A die is thrown 270 times and the results of these throws are given below: No.09. χ = Ei 14 2 Conclusion. Day No.. ILLUSTRATIVE EXAMPLES Example 1. i. The accidents are uniformly distributed over the week. the expected frequencies for each digit is To find the value of χ2 Oi Ei (Oi − Ei ) 2 40 46 36 32 46 196 29 46 289 276 = 46.f. the accidents are uniformly distributed over the week.1428. Null hypothesis H0. If the calculated value of χ2 is greater than the table value. i.21. The following table gives the number of accidents that took place in an industry during various days of the week. the expected frequencies of the accidents on each of these days = Observed frequency Oi Expected frequency Ei (Oi − Ei ) 2 84 = 14. Table value of χ2 at 5% level for (6 – 1 = 5 d. appeared on the die Frequency 1 40 2 32 3 29 4 59 5 57 6 59 Test whether the die is biased or not.e.. 6 59 46 169 57 46 121 59 46 169 . H0 is accepted. the fit is considered to be poor. Sol. Null hypothesis H0. the fit is considered to be good. the divergence between actual and expected frequencies is attributed to fluctuations of simple sampling. Die is unbiased. Test whether accidents are uniformly distributed over the week.e.

.. The following table shows the distribution of digits in numbers chosen at random from a telephone directory: Digits Frequency 0 1026 1 1107 2 997 3 966 4 1075 5 6 7 8 964 9 853 933 1107 972 Test whether the digits may be taken to occur equally frequently in the directory. the expected frequency is given by = = 1000 10 To find the value of χ2 Oi Ei (Oi − Ei ) 2 1026 1000 676 1107 1000 11449 997 996 1075 1000 5625 1107 1000 11449 933 1107 4489 972 1000 784 964 1000 853 1000 1000 1000 9 1156 1296 21609 χ2 = Σ(Oi − E i ) 2 58542 = = 58.e. there is no significant difference between the observed and expected frequency.e.f. I.919. I. of female births No. Null hypothesis H0. The tabulated value of χ2 at 5% level of significance for (6 – 1 = 5) d.. is 11. The tabulated value of χ2 at 5% level of significance for 9 d.f. 10. p = q = 1/2.e. of families 0 4 32 1 3 178 2 2 290 3 1 236 4 0 94 Test whether the data are consistent with the hypothesis that the binomial law holds and the chance of male birth is equal to that of female birth.07 the tabulated value. Ei 1000 Conclusion. 000 Under H0.. is 16.. namely p = q = 1/2. Since the calculated value of χ2 = 21. of male births No.30 > 11. there is a significant difference between the observed and theoretical frequency. . Ei 46 Conclusion. H0 is rejected. Sol.1272 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Σ(Oi − E i ) 2 980 = = 21. Sol. The digits taken in the directory occur with equal frequency. i. the digits taken in the directory do not occur with equal frequency. H0 is rejected. H0 : The data are consistent with the hypothesis of equal probability for male and female births. i.30. I. Records taken of the number of male and female births in 800 families having four children are as follows: No. the die is not unbiased or the die is biased. χ2 = Example 3.542.e.09. Since the calculated value of χ2 is greater than the tabulated value.e. Example 4.

21. H0 is rejected. χ2 = Note.48 178 200 484 2. is 9.82 CHI-SQUARE (χ2) TEST 1273 ________________________________________________________________________________________________________ We use binomial distribution to calculate theoretical frequency given by: N(r) = N × P(X = r) where N is the total frequency. of families with 0 male children = 800 × C0 ⎜ ⎟ = 800 ×1× 4 = 50 2 ⎝2⎠ 4 4 ⎛1⎞ ⎛1⎞ ⎛1⎞ ⎛1⎞ N(1) = 800 × C1 ⎜ ⎟ ⎜ ⎟ = 200.. I. By the Poisson distribution the frequency of r success is mr N(r ) = N × e − m ⋅ .72 3 0 4 Observed frequency Oi Expected frequency Ei (Oi − Ei ) 2 (Oi − Ei ) 2 Ei Σ(Oi − E i ) 2 = 54.49. Verify whether the Poisson distribution can be assumed from the data given below: No. Since the calculated value of χ2 is greater than the tabulated value. i. N(r) is the number of families with r male children: P(X = r) = n Cr p r q n − r where p and q are the probability of male and female births. the degrees of freedom ν = n – 1.42 290 300 100 0. H0 : The Poisson fit is a good fit to the data. n is the number of children. r! Mean of the given distribution = . the data are not consistent with the hypothesis that the binomial law holds and that the chance of a male birth is not equal to that of a female birth. Parameter m = x = 2.48 94 50 1936 38. 1 ⎛1⎞ N(0) = No. Ei Conclusion. The table value of χ2 at 5% level of significance for 5 – 1 = 4 d.333 236 200 1296 6.f. ν = 5 – 1 = 4.e. Example 5. N(4) = 800 × C4 ⎜ ⎟ ⎜ ⎟ = 50 ⎝2⎠ ⎝2⎠ ⎝2⎠ 32 50 324 6.e..433. Since the fitting is binomial. of defects Frequency 0 6 1 13 2 13 3 8 4 4 5 3 Sol. Σ f i xi 94 = =2 Σ fi 47 To fit a Poisson distribution we require m. N(2) = 800 × 4 C 2 ⎜ ⎟ ⎜ ⎟ = 300 ⎝2⎠ ⎝2⎠ ⎝2⎠ ⎝2⎠ 4 1 3 2 2 ⎛1⎞ N(3) = 800 × 4 C3 ⎜ ⎟ ⎝2⎠ 1 ⎛1⎞ ⎛1⎞ ⎛1⎞ 4 ⎜ ⎟ = 200. N is the total frequency.

and 118.. G4 should be in the ratio 9 : 3 : 3 : 1. Since the calculated value of χ2 is less than that of the tabulated value.72 ≈ 13 N(1) = 47 × e ⋅ 1! (2)3 N(3) = 47 × e −2 ⋅ = 8. there is no significant difference between the observed and theoretical frequency under H0.72 ≈ 13.02716 4 4 4.2864.24 0. 2! 4 −2 (2) N(4) = 47 × e ⋅ = 4.e. i. .36 0. is 7.696 ≈ 2.48 0. is 9. i. the theoretical frequency can be calculated as follows: 1600 × 9 = 900.0135 5 3 1. G1. The experimental result supports the theory.49. Since the calculated value of χ2 is less than that of the tabulated value. N(0) = 47 × e ⋅ 0! (2) 2 N(2) = 47 × e −2 ⋅ = 12.f. 4! −2 (2)1 = 12.696 1.24 ≈ 4. The tabulated value of χ2 at 5% level of significance for γ = 6 – 2 = 4 d. Ei Conclusion. The theory predicts the proportion of beans in the four groups. 16 1600 × 3 E(G 3 ) = = 300.5633 287 300 0.e. G2. Ei Conclusion.00616 2 13 12.24 χ2 = Σ(Oi − E i ) 2 = 4. In an experiment with 1600 beans the numbers in the four groups were 882. 16 E(G1 ) = To calculate the value of χ2 Observed frequency Oi Expected frequency Ei (Oi − Ei ) 2 Ei 882 900 0.72 0.f. The table value of χ2 at 5% level of significance for 3 d... 287. hence H0 is accepted. I. the Poisson distribution provides a good fit to the data.36 ≈ 6. H0.7266. 16 1600 × 1 E(G 4 ) = = 100 16 E(G 2 ) = 313 300 0.815.72 0.00616 3 8 8. the experimental results support the theory. The calculated value of χ2 is 1.36 1600 × 3 = 300. G3. 313.48 ≈ 9 3! 5 −2 (2) N(5) = 47 × e ⋅ = 1.1274 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ (2)0 = 6.0026 Σ(Oi − E i ) 2 χ = = 1. 5! −2 X Oi Ei (Oi − Ei ) 2 Ei 0 6 6. Does the experimental result support the theory? Sol.e. Example 6.2864.5633 118 100 3.2037 2 1 13 12. H0 is accepted.

no 5.e. The following results were obtained: No. Poisson law fits the data 2. it was found that 280 students have failed. of errors No. unbiased ________________________________________________________________________________________________________ 21. . of families Mon 65 5 0 14 4 1 56 Tues 54 3 2 110 2 3 88 Wed 60 1 4 40 Thurs 56 0 5 12 Fri 71 Sat 84 3. Examine whether there is any peculiarity. A survey of 320 families with 5 children each revealed the following information: : : : Is this result consistent with the hypothesis that male and female births are equally probable? 4. In a sample analysis of examination results of 500 students. It is found that 4 heads occur 6 times. 2 heads occur 69 times. the attributes are independent and do not bear any association. Discuss whether the coin may be regarded as unbiased.82. Do these figures support the general belief that the above categories are in the ratio 4 : 3 : 2 : 1 respectively? Answers 1. 100 accounts are selected at random and estimated for errors. 3 heads occur 43 times.21. A’s..5 The χ2 Test as a Test of Independence With the help of the χ2 test. yes 4. Thus a very useful application of the χ2 test is to investigate the relationship between trials or attributes. On the other hand. and one head occur 34 times. of accounts : : 0 35 1 40 2 19 3 2 4 0 5 2 6 2 Does this information verify that the errors are distributed according to the Poisson probability law? 7. we can find whether or not two attributes are associated.. accepted 6. and the rest. Fit a Poisson distribution to the following data and the best goodness of fit: x f : : 0 109 1 65 2 22 3 3 4 1 6. 5. accepted 7. The sales in a supermarket during a week are given below. . 4 coins were tossed at a time and this operation was repeated 160 times. we say that the results of the experiment do not support the hypothesis.82 CHI-SQUARE (χ2) TEST 1275 ________________________________________________________________________________________________________ TEST YOUR KNOWLEDGE 1. .e. Test the hypothesis that the sales do not depend on the day of the week. which can be classified into two or more categories. i. The following table gives the frequency of occupance of the digits 0. 170 have gotten C’s. the hypothesis holds true. 1. Days : Sales (in $10000) : No. 9 in the last place in four logarithms of numbers 10–99. In other words.05. 90 have gotten B’s. In the accounting department of a bank. if the calculated value of χ2 is greater than the table value at a specified level of significance. of girls No. i. of boys No. We take the null hypothesis that there is no association between the attributes under study. using a significance level of 0. . maybe 3. Digits : Frequency : 0 6 1 16 2 15 3 10 4 12 5 12 6 3 7 2 8 9 9 5 2. we assume that the two attributes are independent. If the calculated value of χ2 is less than the table value at a specified level (generally 5%) of significance. the attributes are associated. .

1276 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ The sample data are set out into a two-way table.. .. . . B2. a|b 2 Note 1. . 2. B3.e. . s) and (Ai Bj) represent the number of people possessing attributes Ai and Bj.. . . r N (B j ) N (A i B j ) N If (A i B j )0 is the expected number of people possessing both the attributes Ai and Bj (A i B j )0 = NP(A i B j ) = NP(A i )(B j ) (A i ) (B j ) (A i )(B j ) = N N N 2 r s ⎡ ⎡ (A B ) − (A B ) ⎤ ⎤ i j 0⎦ ⎣ i j 2 ⎥ χ = ∑∑ ⎢ ⎢ ⎥ (A i B j )0 i =1 j =1 ⎣ ⎦ =N (∵ A and B are independent) P(A i B j ) = Probability that a person possesses both attributes A i and B j = Hence which is distributed as a χ2 variate with (r – 1)(s – 1) degrees of freedom. frequencies as χ2 = ( a + b)(c + d )(b + d )( a + c ) .. If (Ai). (ArB1) . The contingency table for r × s is given below: A B B1 B2 B3 . . 2. .. .. j = 1.. (A1Bs) (A1) A2 (A2B1) (A2B2) (A2B3) . . r. . (Ar) Total B1 B2 B3 ... (A3Bs) (A3) . 2. A and B are independent under the null hypothesis.. . . . (ArB2) . . . A2. . ... . For a 2 × 2 contingency table where the frequencies are χ can be calculated from independent c d 2 ( a + b + c + d )( ad − bc ) .. . Ar and B divided into s classes B1... . . (A2Bs) (A2) A3 (A3B1) (A3B2) (A3B3) .. . . called a contingency table. .. i. (Bj) represents the number of people possessing the attributes Ai. . . Ar .. Bs Total A1 (A1B1) (A1B2) (A1B3) ... Also we have total frequency.. . . . (ArBs) . Bs. Bj respectively. Let us consider two attributes A and B divided into r classes A1. ... (ArB3) . . . . (i = 1. (Bs) N ∑ Ai = i =1 r ∑B i =1 s j where N is the H0 : Both the attributes are independent.. . A3. . we calculate the expected frequency as follows: P(A i ) = Probability that a person possesses the attribute A i = P(B j ) = Probability that a person possesses the attribute B j = (A i ) i = 1. .. .

Decrease by 1 those cell frequencies that are greater than expected frequencies. and increase by 1 those that 2 2 If the attributes are independent then c are less than expected. If a|b ad − bc is the 2 × 2 contingency table with two attributes. Hence. if the frequencies of a cell is small. In a 2 × 2 table. whole total Note 3. 1 ⎞ ⎛ N ⎜ bc − ad − N ⎟ 2 ⎠ ⎝ 2 After Yates’s correction χ = 2 ( a + c )(b + d )(c + d )( a + b) N ⎜ ad − bc − when ad − bc < 0 χ = 2 ⎛ ⎝ 1 ⎞ 2 ⎠ N⎟ 2 ( a + c )(b + d )(c + d )( a + b) when ad − bc > 0. What are the expected frequencies of the 2 × 2 contingency tables given below: (i) Sol. a = . we make Yates’s correction to make χ2 continuous..e. If the contingency table is not 2 × 2. we have another formula for calculating the expected frequency (AiBj)0 = N Product of column total and row total I. a c b d Observed frequencies a c a+c b d b+d a+b c+d a+b+c+d=N (ii) 2 6 10 6 Expected frequencies (a + c)(a + b) a+b+c+d (a + c)(c + d ) a+b+c+d (b + d )(a + b) a+b+c+d (b + d )(c + d ) a+b+c+d (i) → . Q = is called the coefficient of c d ad + bc association. This will not affect the marginal columns. the expected frequency in each cell is = . cannot be (A i )(B j ) used. This correction is known as Yates’s correction to continuity.82 CHI-SQUARE (χ2) TEST 1277 ________________________________________________________________________________________________________ Note 2. Yate’s Correction. ILLUSTRATIVE EXAMPLES Example 1. then the formula for calculating χ2 as given in Note 1. b d Note 4.21.

they are independent.e. is 3.62) 2 (148 − 259.02) 2 (51 − 167. They are dependent. we calculate the expected frequency in each cell as = Product of column total and row total whole total Expected frequencies are: Eye color of son Eye color of father Light Not light Total Light 619 × 522 = 359. Null hypothesis H0. Since the calculated value of χ2 > the tabulated value of χ2. i. .38 = 261.98 900 619 Not light 289 × 522 = 167.498.f. From the following table regarding the color of eyes of fathers and sons test whether the color of the son’s eye is associated with that of the father. i. Tabulated value of χ2 at 5% level for 1 d. The color of the son’s eye is not associated with that of the father.. Conclusion. the color of the son’s eye is associated with that of the father.62 900 289 × 378 = 121.98) 2 (230 − 121.841.02 900 619 × 378 = 259.e.02 167.38 900 289 Total 522 378 900 χ2 = (471 − 359.1278 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Observed frequencies (ii) 2 6 8 10 6 16 12 12 24 Expected frequencies 8 × 12 =4 24 8 × 12 =4 24 16 ×12 =8 24 16 ×12 =8 24 → Example 2. Under H0. H0 is rejected.62 259..38) 2 + + + 359. Eye color of son Light 471 148 Eye color of father Light Not light Not light 51 230 Sol.98 121.

02864 0.28126 . (A1 )(B2 ) (2850) × (1000) = = 954.27 N 2985 (A )(B ) (135) × (990) (A 2 B2 )0 = 2 2 = = 44.773 N 2985 (A )(B ) (135) × (995) (A 2 B3 )0 = 2 3 = = 45.3110 0 27. the two attributes. The following table gives the number of good and bad parts produced by each of the three shifts in a factory: Good parts Day shift Evening shift Night shift Total 960 940 950 2850 Bad parts 40 50 45 135 Total 1000 990 995 2985 Test whether or not the production of bad parts is independent of the shift on which they were produced. B2.02889 0 0. N 2985 (A1B1 )0 = To calculate the value of χ2 Class (A1B1) (A1B2) (A1B3) (A2B1) (A2B2) (A2B3) Oi 960 940 950 40 50 45 Ei 954. A2. Under H0. The production of bad parts is independent of the shift on which they were produced.e.226 N 2985 (A )(B ) (2850) × (995) (A1B3 )0 = 1 3 = = 950 N 2985 (A )(B ) (135) × (1000) (A 2 B1 )0 = 2 1 = = 45.27 44. ⎡ ⎡(A B ) − (A B ) ⎤ 2 ⎤ i j 0 i j ⎦ ⎥ χ = ∑∑ ⎢ ⎣ ⎥ (A i B j )0 i =1 j =1 ⎢ ⎣ ⎦ 2 2 3 Calculation of expected frequencies Let A and B be two attributes. Null hypothesis H0. are independent.82 CHI-SQUARE (χ2) TEST 1279 ________________________________________________________________________________________________________ Example 3.226 950 45.61022 0 1.3215 0 (Oi − Ei ) 2 / Ei 0. I. production and shifts. namely. Sol.21. production and shifts. A is divided into two classes A1. B3.77 945.61349 0.7729 27..77 N 2985 (A )(B ) (2850) × (990) (A1B2 )0 = 1 2 = = 945. and B is divided into three classes B1.3529 27.773 45 (Oi − Ei ) 2 27.

the production of bad parts is independent of the shift on which they were produced.. Null hypothesis H0. A is divided into 5 classes (r = 5). Example 4.37 N 3883 (A1 )(B2 ) 1136 ×1783 = = 521. find whether hair color and sex are associated.289 N 3883 (A 2 )(B2 ) 1526 × 1783 = = 700. The two attributes of hair color and sex are not associated. B is divided into 2 classes (s = 2).482 N 3883 (A 3 )(B2 ) 955 × 1783 = = 483. we calculate χ = ∑∑ ⎣ (A i B j )0 i =1 j =1 2 5 2 2 Calculate the expected frequency (A i B j )0 as follows: (A1B1 )0 = (A1B2 )0 = (A 2 B1 )0 = (A 2 B2 )0 = (A 3 B1 )0 = (A 3 B2 )0 = (A1 )(B1 ) 1136 × 2100 = = 614. ∴ Degrees of freedom = (r – 1)(s – 1) = (5 – 1)(2– 1) = 4 ⎡(A i B j )0 − (A i B j ) ⎤ ⎦ Under H0.e. they are independent.1280 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Conclusion. The tabulated value of χ2 at 5% level of significance for 2 degrees of freedom (r – 1)(s – 1) is 5. we accept H0.. Color Sex Boys Girls Total Fair 592 544 1136 Red 849 677 1526 Medium 504 451 955 Dark 119 97 216 Black 36 14 50 Total 2100 1783 3883 Sol.991. i.629 N 3883 (A 2 )(B1 ) 1526 × 2100 = = 852.517 N 3883 . Since the calculated value of χ2 is less than the tabulated value.e. Let A and B be the attributes of hair color and sex. respectively. From the following data. i.71 N 3883 (A 3 )(B1 ) 955 × 2100 = = 516.

1641 155. and of these only 35 were attacked.0127 0. the two attributes are not independent.f.482 438. and 343 were vaccinated.3553 0.289 700.799.959 N 3883 Calculation of χ2 Class A2B1 A1B2 A2B1 A2B2 A3B1 A3B2 A4B1 A4B2 A5B1 A5B2 Oi 592 544 849 677 504 451 119 97 36 14 Ei 614.959 (Oi − Ei ) 2 500.e. Conclusion. Example 5.7698 4.71 516..04 22.2816 80. .816 99. Let the two attributes be vaccination and exposed to smallpox. Sol.0480 2.462 10. i.816 N 3883 (A 4 )(B2 ) 216 × 1783 = = 99.517 116.183 27.416 500.495 9.e.629 852.0408 0. Table of χ2 at 5% level of significance for 4 d.183 N 3883 (A 5 )(B1 ) 50 × 2100 = = 27.959 0. the hair color and sex are associated.37 521. is 9.79975 χ2 = 9.800 155.2636 (Oi − Ei ) 2 Ei 0.04 N 3883 (A 5 )(B2 ) 50 ×1783 = = 22. Since the calculated value of χ2 < tabulated value H0 is rejected.8023 0.7654 80..8175 562. i.3016 0.9689 3.488.21. Can vaccination be regarded as a preventive measure of smallpox as evidenced by the following data of 1482 people exposed to small pox in a locality? 368 in all were attacked of these 1482 people. For the given data we form the contingency table.825 4.8145 0. Each attribute is divided into two classes.82 CHI-SQUARE (χ2) TEST 1281 ________________________________________________________________________________________________________ (A 4 B1 )0 = (A 4 B2 )0 = (A 5 B1 )0 = (A 5 B2 )0 = (A 4 )(B1 ) 216 × 2100 = = 116.

I. the vaccination can be regarded as a preventive measure of smallpox.841.e.2261.e. vaccination cannot be regarded as a preventive measure of smallpox. The two attributes are independent.1728 7.2295 2517.1282 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Vaccination A Disease smallpox B Attacked Not Total Vaccinated 35 308 343 Not 333 806 1139 Total 368 1114 1482 Null hypothesis H0.828 282.171 N 1482 Calculation of χ2 Class (A1B1) (A1B2) (A2B1) (A2B2) Oi 35 308 333 806 Ei 85. .9399 48. the two attributes are not independent.1713 N 1482 (A1 )(B2 ) 343 × 1114 = = 257. Degrees of freedom ν = ( r − 1)( s − 1) = (2 − 1)(2 − 1) = 1 Under H0. is 3..1713 257.554 8.828 856. Since the calculated value of χ2 > tabulated value H0 is rejected.1292 (Oi − Ei ) 2 Ei 29.159 2517.828 N 1482 (A 2 )(B1 ) 1139 × 368 = = 282.e. Tabulated value of χ2 at 5% level of significance for 1 d. ⎡(A i B j )0 − (A i B j ) ⎤ ⎦ χ = ∑∑ ⎣ (A i B j )0 i =1 j =1 2 2 2 2 Calculation of expected frequency (A1B1 )0 = (A1B2 )0 = (A 2 B1 )0 = (A 2 B2 )0 = (A1 )(B1 ) 343 × 368 = = 85.171 (Oi − Ei ) 2 2517.229 2517...828 N 1482 (A 2 )(B2 ) 1139 × 1114 = = 856.f. i.5592 2.2261 Calculated value of χ2 = 48. Conclusion. i.

________________________________________________________________________________________________________ 21. can you say the education depends on sex? 2. that of the population. If r is the correlation coefficient of the sample and ρ . 500 students at school were graded according to their intelligences and economic conditions of their homes.83 Z-TEST 1283 ________________________________________________________________________________________________________ TEST YOUR KNOWLEDGE 1. The following data is collected on two characteristics: Smokers Literate Illiterate 83 45 Nonsmokers 57 68 Based on this information can you say that there is no relation between habit of smoking and literacy? 3. calculate the value of . Examine whether there is any association between economic condition and intelligence. In an experiment on the immunization of goats from anthrax. Yes 2. Derive your inferences on the efficiency of the vaccine.21.83 Z-TEST This test is used to test the significance of the correlation coefficient in small samples. No 3. Died from anthrax Inoculated with vaccine Not inoculated 2 6 Survived 10 6 Answers 1. the following results were obtained. from the following data: Economic conditions Good Rich Poor 85 165 Intelligence Bad 75 175 4. Not effective. No 4. In a locality 100 people were randomly selected and asked about their educational achievements. The results are given below: Education Middle Sex Male Female 10 25 High school 15 10 College 25 15 Based on this information.

96 (5% level of signifiS.1284 CHAPTER 21: STATISTICS AND PROBABILITY ________________________________________________________________________________________________________ Z −ξ 1 n−3 where ⎛ 1+ r ⎞ or 1.26 S.5.3 ⎠ ⎝ 1− ρ ⎠ ξ= = 1. therefore.7536 = 0.7. Hence the sample may be regarded as coming from a population with ρ = 0.1513 log10 ⎜ 2 ⎝ 1 − 0.549 ⎛ 1+ ρ ⎞ 1 ⎛ 1 + 0. the correlation is 0.1513 log 5.67 = 1.5 ⎞ log e ⎜ ⎟ = 1.1513 log10 ⎜ ⎟ 2 ⎝ 1− r ⎠ ⎝ 1 − 0. Example 1.5 ⎠ = 1.5 ⎠ = 1.1513 log10 ⎜ ⎟ 2 2 ⎝ 1− ρ ⎠ ⎝ 1− ρ ⎠ Z= 1 1 ⎛ 1+ r ⎞ tanh −1 r = log e ⎜ ⎟ 2 2 ⎝ 1− r ⎠ 1 = S. which is less than 1.3 Z= 1 ⎛ 1+ r ⎞ ⎛ 1 + 0. Is the difference significant? Sol.E.E.31 .1513 log1. n−3 If the absolute value of this level.1513 × 0.7 ⎞ log e ⎜ ⎟ ⎟ = 1.E.857 = 1.1513 × 0. Z= 1 ⎛ 1+ r ⎞ ⎛ 1 + 0.5 ⎞ log e ⎜ ⎟ = 1.55 ⎛ 1+ ρ ⎞ 1 ⎛ 1 + 0. ILLUSTRATIVE EXAMPLES difference exceeds 1.549 − 0.3. 0.26 cance) and is.4771 = 0. r = 0.7.2695 = 0. = = = n−3 15 18 − 3 Z − ξ 0. Sol. From a sample of 19 pairs of observations.E.1513 log 3 = 1.1513 log10 ⎜ ⎟ ⎝ 1− r ⎠ ⎛ 1+ ρ ⎞ ⎛ 1+ ρ ⎞ 1 1 ξ = tanh −1 ρ = log e ⎜ ⎟ or 1.4771 = 0. the difference is significant at 5% S.868 = −0.1513 × 0.23.7 ⎠ ⎝ 1− ρ ⎠ ξ= = 1. The absolute value of Example 2.868 Z − ξ = 0. Test the significance of the correlation r = 0.1513 log10 ⎜ 2 ⎝ 1 − 0. We have to test the hypothesis that the correlation in the population is 0.1513 log10 ⎜ ⎟ 2 ⎝ 1− r ⎠ ⎝ 1 − 0.5 from a sample of size 18 against the hypothetical correlation ρ = 0.319 = = 1. not significant.3 ⎞ log e ⎜ ⎟ ⎟ = 1.319 1 1 1 = 0.7.5 and the corresponding population value is 0.1513 log 3 = 1. Here n = 19.1513 × 0.96. ρ = 0.

24 = = 0.31 = 0.96 (5% level of significance) and is.96 S.25 which is less than 1.24.72 is obtained from a sample of 29 pairs of observations.3.8? Answer 1.E. therefore.E.x = 1 1 1 = = = 0. Can the sample be regarded as drawn from a bivariate normal population in which the true correlation coefficient is 0. TEST YOUR KNOWLEDGE 1.83 Z-TEST 1285 ________________________________________________________________________________________________________ Z − ξ = 0.55 − 0. A correlation coefficient of 0. S.25 19 − 3 4 n−3 ∴ Z − ξ 0. not significant. Yes ________________________________________________________________________________________________________ . 0.21. Hence the sample may be regarded as coming from a population with ρ = 0.

Sign up to vote on this title
UsefulNot useful