Professional Documents
Culture Documents
Notes
Structure:
2.1 Introduction to Measures of Central Tendency
2.2 Average
2.3 Types of Averages
2.4 Arithmetic Mean
2.5 Median
2.6 Mode
2.7 Measure of Dispersion
2.8 Types/Methods of Dispersion
2.9 Range
2.10 Average Deviation / Mean deviation
2.11 Standard Deviation (SD or )
2.12 Summary
2.13 Check Your Progress
2.14 Questions and Exercises
2.15 Key Terms
2.16 Check Your Progress: Answers
2.17 Case Study
2.18 Further Readings
2.19 Bibliography
Objectives
2.2 Average
An average is a single figure which sums up the characteristics of a whole group
of figures. In the words of clark “average is an attempt to find one single figure to describe
whole of figures.
An average is described as a measure of central tendency as it is more or less a
central value around which various values cluster. In the world of CROXTON and COWDEN
“an average is a single value within the range of the data that is used to represent all
of the values in the series. Since an average is somewhere within the range of the data,
it is called a measure of cultural value.
x1 x2 x3 ............. x n
Symbolically x
n
A) Individual Series
1. Direct Method
The following steps are involved in calculating arithmetic mean under individual series
using direct method:
1. Add up all the values of all the items in the series.
2. Divide the sum of the values by the number of items. The result is the arithmetic
mean.
The following formula is used:
x
X = N
Illustration - 1
Value (x): 125 128 132 135 140 148 155 157 159 161
Solution:
Calculation of arithmetic mean:
N = 10 x = 1,440
x 1,440
X = 144
n 10
Illustration - 2
The monthly income of ten families of a certain locality are given in rupees as below:
Family A B C D E F G H I J Notes
Income (in `) 850 700 440 750 500 800 420 2500 2300 1500
Calculate the arithmetic mean.
Solution:
Calculation of arithmetic mean:
N = 10 x = 11,160
x 11160
X = = 1,116
N 10
The average income of 10 families is ` 1,116
The following steps are involved in calculating arithmetic mean under individual series
using short-cut or indirect method:
1. Assume one of the values in the series as an average. It is called as working
mean or assumed average.
2. Find out the deviation of each value from the assumed average.
3. Add up the deviations
4. Apply the following formula.
d
X = A
N
where, X = Arithmetic mean
A = Assumed average
d = Sum of the deviations
N = Number of items
Notes Illustration - 1
Calculate the arithmetic average of the data given below using short–cut method.
Roll No. 1 2 3 4 5 6 7 8 9 10
Marks obtained. 43 48 65 57 31 60 37 48 78 59
Solution:
Calculation of Arithmetic mean:
1 43 – 17
2 48 – 12
3 65 +5
4 57 –3
5 31 – 29
6 60 0
7 37 – 23
8 48 – 12
9 78 + 18
10 59 –1
d = – 74
d 74FG IJ
X = a
N
60
10 H K = 60 – 7.4 = 52.6 marks.
Illustration - 2
The following data relates to sizes sold at a store during a given week. Find the
average size by the short cut method.
Size of store No. of pairs
4.5 1
5 2
5.5 4
6 5
6.5 15
7 30
7.5 60
8 82
8.5 82
9 75
9.5 44
10 25
10.5 15
11.0 4
Solution: Notes
Calculation of Arithmetic mean:
fd 169.5
X = a 8
N 444
= 8 + 0.38 = 8.38
The average size of stores sold is 8.4
Illustration - 3
From the following figures find the mean using indirect method.
Marks No.of persons.
0 – 10 5
10 – 20 10
20 – 30 20
30 – 40 40
40 – 50 30
50 – 60 20
60 – 70 10
70 – 80 4
Notes Solution:
Calculation of mean:
fd 780 FG IJ
X =
a
N
45
139 H K
= 45 + ( – 5.6) = 39.4 marks
The following steps are involved in computing mean under step deviation method:
1. Find out the mid–value of each group or class.
2. Assume one of the mid–values as an average.
3. Find out the deviation of each mid–value from the assumed average in terms
of class interval.
4. Multiplying the deviation of each class by its frequency.
5. Add up the products.
6. Apply the following formula
fd
X = A i
N
A = Assumed average
fd = Sum of the deviations in terms of class interval
N = Total frequency
i = Class interval
Illustration - 1
Solution: Notes
xA
Marks (CI) No. student(f) Midvalue(x) d= fd
5
0-05 2 2.5 -3 -6
5-10 4 7.5 -2 -8
10-15 5 12.5 -1 -5
15-20 3 17.5 0 0
20-25 2 22.5 +1 +2
25-30 4 27.5 +2 +8
30-35 5 32.5 +3 +15
n = 25 d = 0 fd = 6
Using step deviation formula Assumed Mean (A) = 17.5
Common factor (i) is 5
fd 6 30
x = A i = 17.5 + 5 = 17.5 +
n 25 25
B) Discrete Series
In the discrete series, every term (i.e. value of x) is multiplied by its corresponding
frequency (fx) and then their total (sum) fx is divided by the total frequency (N) or f .
1. Direct Method
fx
Formula: x
n
Illustration - 1
Marks No. of fx
(x) Students (f)
35 3 105
40 8 320
45 12 540
50 9 450
55 4 220
60 7 420
65 15 975
Amity Directorate of Distance and Online Education
32 Quantitative Techniques in Management
Notes 70 5 350
75 10 750
80 7 560
85 5 425
90 3 270
95 2 190
N = 90 fx = 5,575
fx 5,575
x = = 61.95
n 90
2. Indirect Method
fdx
Formula: x
n
Illustration - 1
N = 90 fdx = -275
fdx -275
x = 60 + = 60 - 3.05 = 56.95
n 90
Illustration - 1
x A
x f dx = c
(i = 5) fdx
N = 90 fdx = –55
fdx -55 -275
xA i = 65 + × 5 = 65 + = 65 - 3.05 = 61.95
n 90 90
C) Continuous Series
In continuous series variable are represented by class-interval. Each class intervals
has its own frequency. Midpoint (class-marks) of each class should be ascertained first.
Then the procedure of finding the arithmetic mean is the same as used in the discrete
series.
i) Direct Method
Illustration - 1
fx 2,330
x = = 46.6
n 50
Illustration - 1
N = 50 fdx = 8
fdx
xA i
n
8 80
= 45 + × 10 = 45 + = 45 + 1.6 = 46.6
50 50
2. Inclusive Method
Illustration - 1
The following are the 270 soybean plant heights collected from a particular plot. Find the
arithmetic mean of the plants
Plant height 8-12 13-17 18-22 23-27 28-32 33-37 38-42 43-47 48-52
(Cms)
No. of plants 8 17 20 50 75 30 25 40 5
When the length of class is equal step deviation method is appropriate and the length of
the class unequal direct method is appropriate, in this problem the length of class is equal i.e.,
c = 5 whether inclusive or exclusive given continuous class converted in to mid point(x) for
calculating Arithmetic Mean
Solution:
x A
Plant height No. of Mid point (x) dx = c
A = 30 (f × dx) = fdx (Cms) (x)
LL UL
plants (f) 2
i=5 dx
U|
|V
8-12 8 8 + 12/2 = 10 (10 – 30)/5 = –4 (8 × –4) = –32
13-17 17 13 + 17/2 = 15 (15 – 30)/5 = –3 (17 × –3) = –51
18-22 20 18 + 22/2 = 20 (20 – 30)/5 = –2 (20 × –2) = –40 ||
23-27 50 23 + 27/2 = 25 (25 – 30)/5 = –1 (50 × –1) = –50 W –173
28-32 75 28 + 32/2 = 30(A) (30 – 30)/5 = 0 (75 × 0) = 0 U|
33-37 30 33 + 37/2 = 35 (35 – 30)/5 = 1 (30 × 1) = 30 |V
38-42 25 38 + 42/2 = 40 (40 – 30)/5 = 2 (25 × 2) = 50 ||
43-47 40 43 + 47/2 = 45 (45 – 30)/5 = 3 (40 × 3) = 120 W
48-52 5 48 + 52/2 = 50 (50 – 30)/5 = 4 (5 × 4) = 20 +220
Notes
fdx 47 235
xA i = 30 + 5 = 30 + = 30 + 0.870 = 30.87 or 30.9
n 270 270
The lower limit of the first class interval and upper limit of the last class interval are
not know, it is called open-end classes.
Illustration - 1
“ 90 85 80-90 18 85 +3 54 Notes
“ 100 100 90-100 15 95 +4 60
N = 100 fdx = 59
fdx 59 590
xA i = 55 + 10 = 55 + = 55 + 5.9 = 60.9
n 100 100
Illustration - 1
N = 100 fdx = 27
fdx 27 270
xA i = 55 + 10 = 55 + = 55 + 2.7 = 57.7
n 100 100
The simple arithmetic mean it is assumed that all the items are of equal importance
for finding simple average total values are divided by number of items.
Sometime, some observations got relatively more importance than other observation.
The weight for such observation should be given on the basis of their relative importance.
The value of each item is multiplied by its weight and the product are divided by number
of weights for finding average is called weight arithmetic mean.
wx
Symbolically: xw
w
Illustration - 1
Where, n1 = No. of items of the first group, n2 = No. of items of the second group
x1 = A.M of the first group, x 2 = A.M of the second group, x12 = Combined AM
Illustration - 1
From the following data ascertain the combined mean of a factory consisting of 2
branches namely branch A and Branch B. In branch A the number of workers is 500,
and their average salary of ` 300. In branch B the number of workers is 1,000 and their
average salary is ` 250
Solution:
Let the no. of workers in branch A be n1 = 500, Average salary x = 300
1
Let the no. of worker in branch B be n2 = 1,000, Average salary x = 250
2
n . x + n2 . x 2 500(300) + 1000(250) 1,50,000 + 2,50,000
x 12 = 1 1 = =
n1 + n2 500 + 1,000 1,500
4,00,000
= = 266.66
1,500
Correct x
Correct x
N
Illustration - 1
Solution:
882
Correct x = = 44.1
20
Illustration - 1
If the average wage paid to 25 workers is 796, find the missing numbers
Wages 500 600 700 800 900 1,000 1,100
No. of workers 1 3 - - 6 2 1
Solution:
N = 25, AM = 796 Let, missing number of workers be X & Y
Step 1: 1 + 3 + x + y + 6 + 2 + 1 = 25
13 + x + y = 25 x + y = 25 - 13 x + y = 12 (Equation no. 1)
Step 2: X
fx , 796 = (10,800 + 700x + 800y) / 25
N
Cross multiplying 796*25 = 10,800 + 700x + 800y
19,900 - 10,800 = 700x + 800y
700x + 800y = 9100 (Equation no. 2)
Step 3: Equation 1 is multiplying with 700
x + y = 12…..*700, 700x +700y = 8,400 (Equation no. 3)
Step 4: Equation 3 is subtracted from equation 2
700x + 800y = 9,100 (Equation 2) –
700x + 700y = 8,400 (Equation 3)
100y = 700 y = 700/100, y=7
Step 5: Substitute the value of Y in equation no. 1
x + y = 12, x + 7 = 12, x = 12 - 7, x = 5
The missing frequencies are x = 5 and y = 7 respectively.
Amity Directorate of Distance and Online Education
Summary Statistics 41
Merits of Median
Demerits of Median
1. Individual Series
Where, M = Median
N = Number of items
Notes Illustration - 1
FG N 1IJ
Median = Size of H 2 K th item
10
= = 5th item, i.e. 25
2
Illustration - 2
The table below gives the marks obtained in advanced accountancy by the students
with Roll Nos. 1 to 10 at the final chartered accountant examination.
Roll No. Marks obtained
1 43
2 48
3 65
4 57
5 31
6 60
7 37
8 48
9 78
10 59
Calculate the median.
Solution: Notes
Calculation of median:
FG N 1IJ
Median = Size of H 2 K th item
10 1
= 5.5th item.
2
5.5 is between 5th item and 6th item.
48 57 105
i.e., = = 52.5 Median marks is 52.5
2 2
2. Continuous Series
N
2) Find out the median item, i.e., th item.
2
3) Find out the group or class containing the median
4) Estimate the median applying the following formula.
n
cf
Me = l+ 2 i
fm
where Me = Median
l = Lower limit of the median class
cf = Cumulative frequency of the class preceding the median
class
i = Size of class interval
fm = Middle one of frequency sequence.
Notes N
Median is the =
2
Illustration - 1
n 240
M= = 120th item. i.e., 60 – 80 group.
2 2
n
cf 20
Me = l + 2 i = 60 85 70 = 60 + 16.47 = 76.47
fm
Illustration - 2
N 90
M= = 45
2 2
n
cf 50 40
Me = l + 2 i = 40
fm 28
10
= 40 13
28
= 40 + 4.64 = 44.64
Illustration - 1
Class (x) f cf
110-120 6 6
120-130 25 31
130-140 48 79 cf
140-150 72 f 151
150-160 60 211
160-170 19 230
N = 230
Step 1: Mid value convert in to exclusive class, find the difference between two mid
values and half of the difference should be deduct from the mid value to find out lower
limit of the class and the same difference add to the mid value to get upper limit of the
class e.g. (125 - 115) = 10/2 = 5, (115 - 5 = 110 lower limit and 115 + 5 = 120 upper
limit, i.e., 110 - 120………)
Amity Directorate of Distance and Online Education
46 Quantitative Techniques in Management
N
cf
M l1 2 l2 l1
Steps 4: Apply formula f
115 - 79 36 360
= 140 + 150 - 140 = 140 + 72 10 = 140 + = 140 + 5 M = 145
72 72
Illustration - 2
Mid value 35 45 55 65 75 85
Frequency 6 25 18 32 15 4
Solution:
Class (x) f cf
30-40 6 6
40-50 25 31
50-60 18 49 cf
60-70 32 f 81
70-80 15 96
80-90 4 100
N = 100
Mid value convert in to exclusive class, e.g., (35 - 45) = 10/2 = 5, (35 - 5 =
30 lower limit and 35 + 5 = 40 upper limit, i.e., 30 - 40………)
Determine median class. Use N/2 th items
100/2 = 50 terms. l1 = 60, l2 = 70, cf = 49 f = 32
Formula:
N
cf
M l1 2 l2 l1 50 - 49
= 60 +
f 70 - 60
32
1 10
= 60 + 10 = 60 + = 60 + 0.3125, M = 60.312
32 32
Illustration - 1
Less than 10 20 30 40 50 60 70 80
Frequency: 4 16 40 76 96 112 120 125
Solution:
Steps 1: Need to ascertain lower limit of the continuous class (LL = UL - CL) Class
length (CL) = 20 - 10 = 10 i.e., (10 - 10 = 0…………)
Steps 2: Cumulative frequency convert in to sample frequency.
Steps 3: Determine median class. Use N/2 th items 125/2 = 62.5 terms.
N = 125
N
cf
M l1 2 l2 l1 62.5 - 40
= 30 +
f 36 40 - 30
22.5 225
= 30 + 10 = 30 + = 30 + 6.25 = 36.25
36 36
Illustration - 2
More than 10 20 30 40 50 60 70 80
Frequency: 115 103 88 68 43 23 13 3
Solution:
1. Need to ascertain upper limit of the continuous class (UL = LL + CL)
Class length (CL) = 20 - 10 = 10 i.e., (10 + 10 = 20…………)
2. Cumulative frequency convert in to sample frequency
3. Determine median class. Use N/2 th items 115/2 = 57.5 terms
Notes
Value (x) Class cf f
More than 10 10-20 115 - 103 = 12 12
More than 20 20-30 103 - 88 = 15 27
More than 30 30-40 88 - 68 = 20 47
More than 40 40-50 68 - 43 = 25 72
More than 50 50-60 43 - 23 = 20 92
More than 60 60-70 23 - 13 = 10 102
More than 70 70-80 13 - 3 = 10 112
More than 80 80-90 3 115
N = 115
N
cf
M l1 2 l2 l1 57.5 - 47
= 40 +
f 25 50 - 40
10.5 105
= 40 + 10 = 40 + = 40 + 4.2 = 44.2
25 25
Illustration - 1
Complete the following distribution, if its median is 260 & total frequency is 150.
Size 100-150 150-200 200-250 250-300 300-400 400-500 500-600
Frequency 12 - 40 50 - 5 2
Solution:
Size f cf
100-150 12 12
150-200 x 12+x
200-250 40 52+x
250-300 50 102+x
300-400 y 102+x+y
400-500 5 107+x+y
500-600 2 109+x+y
N = 150
Let missing frequency be x and y
N 150
= = 75,
2 2
N
cf
M l1 2 l2 l1
f
75 - (52 + x)
260 = 250 + 50 300 - 250
75 - 52 + x
260 250 50 10 = 23 - x x = 23 - 10 x = 13
50
Substitute in Eq1, 109 + 13 + y = 150 y = 150 - 122 y = 28
Illustration - 2
Height in No. of cf
Inches (CL) plants (f)
5.05 - 6.05 3 3
6.05 - 7.05 8 11
7.05 - 8.05 27 38
8.05 - 9.05 x 38+x
9.05 - 10.05 17 55+x
10.05 - 11.05 11 66+x
11.05 - 12.05 9 75+x
N = 75+x
Median value is given 8.53 inches so,
N 75 + x
Median class is 8.05 - 9.05, =
2 2
N
cf
M l1 2 l2 l1
f
Notes
75 + x
2 - 38
8.53 = 8.05 - 9.05 - 8.05
x
75 + x 75 + x
2 - 38 2 - 38
8.53 = 8.05 - 1 0.48 - 1
x x
75 + x
0.48(x) - - 38 2(0.48x)- 75 + x = -(38)2
2
-1
-0.04x = -1 x= x = 25
-0.04
Steps 1: given inclusive convert in to exclusive (6.1 - 6 = 0.1/2 = 0.05),
Lower limit 5.1 - 0.05 = 5.05 upper limit 6 + 0.05 = 6.05 i.e., (5.05 - 6.05 ……)
Step 2: let missing frequency be x, sample frequency convert in to cumulative
frequency.
2.6 Mode
The word “mode” is derived from the French word “1a mode” meaning fashion. So
it can be regarded as the most fashionable item in the series or the group.
Croxtan and Cowden regard mode as “the most typical of a series of values”. As
a result it can sum up the characteristics of a group more satisfactorily than the arithmetic
mean or median.
Mode is defined as the value of the variable which occurs most frequently in a
distribution. In other words it as the most frequent size of item in a series.
Merits of Mode
Demerits of Mode
Ungrouped Data
a) Individual Series
The mode of this series can be obtained by mere inspection. The number which
occurs most often is the mode.
Illustration - 1
c) Continuous Series
Notes
fm f1
Mo = l+ i
2 fm f1 f 2
where Mo = Mode
l = lower limit
fm = Highest frequency
f1 = Preceding value of highest frequency
f2 = Succeeding value of highest frequency
i = Size of class interval
Illustration - 1
fm f1 12 - 8
Mode = l + i = 35 + 40 - 35
2 fm f1 f 2 2(12)-8-7
4 20
= 35 + 5 = 35 + = 35 + 2.22 = 37.22
24-15 9
Illustration - 2
40-49 25 Notes
50-59 14
60-69 10
70-79 8
80-89 4
fm f
1 25-22
Mode = l + 2 fm f f i = 39.5 + 49.5 - 39.5
1 2 2(25)-22-14
3 30
= 39.5 + 10 = 39.5 + = 39.5 + 2.143 Z = 41.64
50-36 14
d) Calculate Mode when Less than and more than classes are given
Illustration - 1
Less than 10 20 30 40 50 60 70 80
Frequency: 4 16 40 76 96 112 120 125
Solution:
Need to ascertain lower limit of the continuous class (LL = UL - CL) Class length
(CL) = 20 - 10 = 10 i.e., (10 - 10 = 0…………)
fm f
1 36 - 24
Z = l + 2 fm f f i = 30 + 40-30
1 2 2(36) - 24 - 20
12 120
= 30 + 10 = 30 + = 30 + 4.285 Z = 34.285
72 - 44 28
Illustration - 2
More than: 10 20 30 40 50 60 70 80
Frequency: 115 103 88 68 43 23 13 3
Notes Solution:
Need to ascertain upper limit of the continuous class (UL = LL + CL) Class
length (CL) = 20 - 10 = 10 i.e., (10 + 10 = 20…………)
fm f1 25 - 20
Z= l+ i = 40 + 50-40
2 fm f1 f 2 2(25) - 20 - 20
5 50
= 40 + 10 = 40 + = 40 + 5 Z = 45
50 - 40 10
When mode is ill defined, it is difficult to find the value of mode, a sort of empirical
relationship exist among the mean, median and mode in such a way that the median
lies between the mode and the mean. The mode departs (to the left i.e., positive skewed)
2/3 difference from the median and the mean departs (to the right i.e., negatively skewed)
1/3 difference from the median. Karl Pearson’s expressed this relationship as Z = 3M -
2 X (when it is positive skewness).
Illustration - 1
Solution:
Z = 3M - 2X
Illustration - 2
M = ? AM = 39 Z = 36.5
Solution:
Z = 3M - 2X
Illustration - 1
The histogram for the following the data and locate mode graphically.
Class-interval Frequency
0 - 50 6
50 - 100 8
100 - 150 10
150 - 200 3
200 - 250 4
Solution:
Class-interval Frequency
0 - 50 6
50 - 100 8
100 - 150 10
150 - 200 3
200 - 250 4
10 - 8 2 100
Verify: 100 + × 50 , 100 + × 50 , 100 + , Z = 111.1
2(10) - 8 - 3 20 - 11 9
Notes Illustration - 2
Monthly profits of 100 shops are distributed as follows; Locate mode graphically.
Z = 128
Distribution A 50 50 50 X 50 Notes
Distribution B 30 45 75 X 50
The two distributions have same mean i.e. 50. But we cannot say that the
performances of the two distributions are same. There is greater uniformity of performance
in the distribution A. Whereas there is more variability in the performance of the distribution
B. Hence, distribution B are widely scattered. It is clear that the measures of the central
tendency is alone not sufficient to describe the data.
Meaning of Dispersion
The terms dispersion is used in two Senses. First, it means that all the items in
the group are not of the same value. They differ from one another in size. There is no
uniformity in size. Second, dispersion is used to indicate the measure of differences of
the size of items in the group from their average thus, a measure of deviations of items
from there average is called “the measure of dispersion.
Absolute measures: The dispersion results are expressed in terms of the amount
of variation i.e., in original units are called absolute measures, for example range, mean
deviation, standard deviation etc.
Relative measures: The dispersion results are expressed in terms of the degree
of variation i.e., ratios or percentages are called relative measures, for example the
coefficient of range, the coefficient mean deviation, the co-efficient of variation etc.
Q Q
Quartile Deviation 3 1 ............. absolute measure.
2
2.9 Range
It is a measure of dispersion Which gives the difference between the highest and
the lowest value in the series. The difference between the two extreme values is called
the range. Suppose the weight of 50 B.Com students are given. Suppose the minimum
weight is 95 pounds and maximum 135 pounds. The weights of the students are distributed
between the two limits of 95 and 135 pounds. The range is 40 pounds (i.e. 95 – 45).
In any statistical series, the difference between the largest and the smallest values
is called as the range, Thus Range (R = L - S)
Where, L is the largest value and S is the smallest value in the given data. Notes
Co-efficient of Range: The relative measure of the range. It is used in the comparative
L S
study of the dispersion Co-efficient of Range =
L S
Merits of Range
Limitations of Range
Notes Solution:
R=L-S Here, R = 2, L = 12, 2 = 12 - S, S = 12 - 2 S = 10 kgs
Illustration - 2
The following are the wages of 8 workers of a factory find the range of variations and
also compute it’s co-efficient.
Wages (Rs.) 1,400 1,450 1,520 1,380 1,485 1,495 1,575
Solution:
The largest value in the given distribution is 1575 and the smallest value is 1380
R = L - S R = 1,575 - 1,380 R = 195
Illustration - 3
Compute the range and it’s co-efficient of range for the following distribution.
Variable: 30 45 67 24 56 98 25 86 45 34 65
72
Frequency: 4 6 9 8 7 13 18 9 25 23 45
9
Solution:
For finding range, the frequencies are not taken into account
R = L - S, L = 98, S = 24, R = L - S, R = 98 - 24 R = 74
L S 98 24 74
Co-efficient of Range = = 0.607
L S 98 24 122
Illustration - 4
Compute the range and it’s co-efficient of range of the series, and state which one is
more dispersed and more uniform
Series Variables
I 20 22 24 29 27 26 29 21 25
II 61 64 68 66 67 63 69 62 60
III 91 92 93 94 95 96 97 98 99
Solution:
29 20 9 9 99 91 8 Notes
= 0.1836 = 0.069 = 0.042
29 20 49 129 99 91 190
Solution:
Range = Largest – Smallest = 84 – 16 = 68
LS 84 16 68
Coefficient of range = 0.68
LS 84 16 100
Illustration - 6
Compute the range and the co-efficient of range from the following distribution
C.I : 120 - 130 130-140 140-150 150 - 160 160-170
F : 2 9 16 12 5
Solution:
In finding the range the frequencies are never taken into account. The upper limit of
the highest class and the lower limit of the smallest class are only taken into account.
Range = L - S = 170 - 120 = 50
L S 170 120 50
Co-efficient of Range = = = 0.1724
L S 170 120 290
Illustration - 7
From the following distribution find the range and the co-efficient of range
X: 6 12 18 24 30 36 42
y: 20 130 80 60 210 1500 600
Solution:
In finding the range the frequencies are never taken into account.
Range = L - S = 42 - 6 = 36
L S 42 6 36
Co-efficient of Range = = 0.75
L S 42 6 48
Notes Mean deviation is the average amount of variations of the items in a distribution from
either the mean or the median or the mode, ignoring the signs of these deviations. It is
concerned with the extent to which the values are dispersed about the mean or the median
or the mode. In aggregating the deviation ignoring the negative sign.
The following steps are involved in calculating mean deviation in individual series:
(1) Find out an average i.e., either mean or median.
(2) Find out the deviation of each value or size of item from the average selected.
Signs should not be taken into account. The symbol for deviation ignoring sign
is | d |, pronounced as module D.
(3) Add up deviations and divide the sum of the deviations by the number of items.
The formula is as follows:
MD =
|d|
N
where, MD = Mean deviation
| d | = Sum of the deviations from the average ignoring the Signs
N = Number of items
The following steps are involved in calculating mean deviation under discrete Series:
(1) Find out on average (i.e., mean or median).
(2) Find out the deviation of each size from the average selected. All deviations
must be regarded as positive.
(3) Multiply the deviation of each size by its frequency.
(4) Add up the Products (f|d|) and divide the sum of the products by total frequency.
The formula is as follows:
M.D =
f|d|
N
M.D M.D
Co-efficient of MD = or
Mean Median
i) MD in Individual series
Example 1:
Calculate mean deviation and it coefficient for the following data
Value (x) 125 128 132 135 140 148 155 157 159 161
Solution:
Example 2:
Calculate mean deviation and it co-efficient for the following data
Notes X 35 40 45 50 55 60 65 70 75 80 85 90 95
f 3 8 12 9 4 7 15 5 10 7 5 3 2
Solution:
Example 3:
Calculate mean deviation and its co-efficient for the following data:
X f
10-20 5
20-30 4
30-40 7
40-50 12
50-60 10
60-70 8
70-80 4
Solution:
Notes
MD
dx MD
fdx
n n
MD MD
Co-efficient of MD = Co-efficient of MD =
M M
Example 4:
Compute mean deviation and its co-efficient from Median
Value(x) 20 25 30 38 42 55 66 67 70
Solution:
Example 5:
Compute mean deviation and its co-efficient from median
Value(x) : 125 126 130 132 134 138 140 141
f : 8 4 3 10 7 9 4 2
Solution:
Example 6:
Calculate mean deviation and its coefficient form median
x 0-10 10-20 20-30 30-40 40-50
f 8 30 40 12 10
Solution:
Notes
x f
120-140 5
140-160 12
160-180 18
180-200 22
200-220 16
220-240 10
240-260 8
260-280 4
Solution:
x f MP x-z = dx fdx
N = 95 fdx = 2,710
Illustration - 1
Calculate the mean deviation from the airthmatic mean of the following data relating
to the monthly earnings for a year
Months Jan Feb Mar Apr May June
Earnings 1198 1200 1200 1202 1202 1204
Months July Aug Sept Oct Nov Dec
Earnings 1204 1206 1206 1208 1208 1210
Solution:
Calculation of M.D
x = 14,448 |d| = 36
x 14448 1204
x =
N 12
MD =
|d| 36 3
12 12
Illustration - 2
Calculate (a) Median co-efficient of dispresion and (b) Mean Co-efficient of dispersion
from the following data:
n 21
M= = 10.5th item = size of 10.5th item is 8
2 2
MD =
f|d| =
68
3.2
N 21
M.D 3.2
Median co-efficient of Dispersion = = = 0.4
Median 8
Calculation of the Mean co-efficient of dispersion
4 2 8 5.7 11.4
6 4 24 3.7 4.8
8 5 40 1.7 8.5
10 3 30 0.3 0.9
12 2 24 2.3 4.6
14 1 14 4.3 4.3
16 4 64 6.3 25.2
N = 21 fx = 204 f | d | = 59.7
fx
204
x N 21
= 9.7
MD =
f|d| 59.7 2.84
N 21
M.D 2.84
Mean co-efficient of dispersion = = 0.29
Mean 9.7
Notes Illustration - 3
10 - 14 12
15 - 19 29
20 - 24 59
25 - 29 75
30 - 34 46
35 - 39 19
Solution:
Since there is a an inclusive class interval distribution, we shall convert it into
exclusive class interval series.
f|d|=1225
n th
cf n
Median 2 Median is the size of items
l x i 2
fm
th
120 100 240
= 24.5 5 = 120 th items
75 2
20 5
= 24.5 Here, l = lower units = 24.5
75
100
= 24.5 cf = cumulative frequency = 100
75
= 24.5 + 1.33 fm = frequency value = 75
= 25.83 i = size of class interval = 5
= 26 Median = ?
Median = 26
f | d | 1225 Notes
Mean deviation = = 510
.
N 240
Illustration - 4
Calculate mean deviation and its co-efficient value for the following series:
fx 1920
x = = = 19.6
N 98
f| d | 413.6
MD = = = 4.22
N 98
M.D 4.22
Co-efficient of MD = =
19 .6
= 0.215
x
Illustration - 5
Calculate the value of Co-efficient of mean deviation (from median) of the following
data.
To find Median
th th
n 100
50 th item
2 2
n
cf
Median l 2 x i
fm
Where, l = Lower limit of median class
cf = Cumulative frequency of pre-median class
fm = Frequency of median class
i = Size of class interval
50 38 12
50 10 50 10
25 25
120
50 50 4.8 54 .8
25
f | X Me| f|d|
Median deviation = =
N N
1290
= 12.9
100
12.9
= = 0.235
54.8
d 2
symbolically =
n
Co-efficient of Variation
Standard deviation
CV = 100
Mean
The series for which the co-efficient of variation (CV) is greater is said to be called
more variation and less uniformity. On the other hand the series for which co-efficient of
variation (CV) is less is said to be called less variable and more stable or consistency.
Variance
Notes Variance is defined as the mean of the Squares of deviation from the mean. It is
also called mean Square deviation. In order to calculate variance, we must first find out
the mean of the series. The deviation of each size from mean is found out. The deviations
are Squared and added up. The Sum of the Squares of deviations must be divided by
the total number of items. The result is the variance.
Variance =
d2
N
The combined standard deviation can be calculated by following the same method
of calculating the combined mean of two or more than two groups. It may be denoted
by 12 formula for combined standard deviation of two groups is,
Where, d 2 x x d22 x 2 x12
1 1 12
There is exists a relationship between the standard deviation and quartile deviation;
and between standard deviation and mean deviation. Among this quartile deviation is the
smallest and the standard deviation is the largest one. The mean deviation lies between
standard deviation and quartile deviation.
3 5 Notes
Symbolically = QD and = MD
2 4
The differences between mean deviation and Standard deviation are as follows:
(1) In Calculating Mean deviation, Signs are ignored Whereas in Calculating
Standard deviation Signs are taken into account.
(2) Mean deviation can be found out either from mean or median, Whereas Standard
deviation is always calculated from the mean because the sum of the Squares
of the deviation of items from arithmetic mean is the least.
Formula for calculating Standard Deviation and its Co-efficient
( x x )2 f ( x x )2
Actual Mean Method
N N
d2 fd2
Or =
N N
Assumed Mean
d2 F d I
2 2
fd2 fd
a) Short cut method =
N GH N JK
N
N
2
d 2 d
b) Step deviation method
N
C
N
2
fd 2 fd
N
C
N
a) First Calculate arithmetic mean i.e., ( x ).
b) Calculate deviation from the arithm\etic mean i.e., x x dx .
Notes d) Multiply dx 2 with the respect frequency the result will be fdx 2 (only in discrete
and continuous series).
e) Total the dx 2 column in case of individual series and fdx 2 in case of discrete
and continuous series.
f) Apply formula to get standard deviation.
x A
a) Calculate deviation from the assumed mean i.e., dx .
c
b) Square the deviation in order to remove the sign of deviation i.e., dx 2 .
c) Total the dx 2 column in case of individual series and fdx^2 in case of discrete
and continuous series.
d) Apply formula to get standard deviation.
i) Individual Series
Example 1:
X : 120 125 130 135 140 145 150 155 160 165
Solution:
Assumed Mean Method
Example 2:
Calculate SD and variance from the following data:
Wages : 50 60 70 80 90 100 110 120
No. of workers : 8 5 9 4 6 7 3 2
Solution:
Notes a) Calculation of SD
b) Calculation of Variance
Example 3:
Find standard deviation from the following data:
Wages 0 - 10 10 - 20 20 - 30 30 - 40 40 - 50 50 - 60 60 - 70 70 - 80
No. 5 9 8 12 10 4 3 2
Solution:
Notes
Illustration - 1
Calculate the mean and Standard deviation of the marks of 10 Students in Statistics.
Student: 1 2 3 4 5 6 7 8 9 10
Marks in Statistics: 84 51 91 60 68 62 86 58 53 47
Solution:
Calculation of Standard deviation
Student Marks in Statistics d = 66 d2
1 84 +18 324
2 51 –15 225
3 91 +25 625
4 60 –6 36
5 68 +2 4
6 62 –4 16
7 86 +20 400
8 58 –8 64
9 53 –13 169
10 47 –19 361
x = 660 d = 0 d2 = 2,224
x 660 66
x =
N 10
=
d2 2224
=
222.4 = 14.91 Marks
N 10
14.19
Co-efficient of Variation = 100 = 100 = 22.59%
x 66
Illustration - 2
Calculate the Standard deviation and the Co-efficient of variation from the following
table
Notes 30 – 40 61
40 – 50 132
50 – 60 153
60 – 70 140
70 – 80 51
80 – 90 2
Solution:
Calculation of Standard deviation and Co-efficient of Variation
fd FG 150 IJ
x = a
N
= 55 + H 542 K = 55 + (– 0.28) = 54.72 years
fd2 F fd I FG IJ
2
=
N GH N JK =
76500
542
150
542H K
= . (0.28)2
14114 = 140.356 = 11.85
11.85
Cv = 100 = 100 21.65%
x 54.72
Illustration - 3
Following are the runs scored by the two batsmen named NEKO and DECO in ten
innings. Find who is better scorer and who is more consistent.
NEKO: 101 22 0 36 82 45 7 13 65 14
DECO: 97 12 40 96 13 8 85 8 56 16
Computation of Standard Deviation.
Solution:
d2 10546.50
s = 1054.65 =32.475
n 10
32.475
C.V = 100 100 = 84.35 %
X 38.5
DECO
X 431
x = = 43.1
n 10
35.647
C.V. = x 100 x 100 = 82.71%
x 43.1
DECO is a better run score and more consistent player than NEKO (because
his average is more and variation is less)
Illustration - 4
Following are the marks obtained by two students A and B in 10 tests of 100 marks
each.
Tests: 1 2 3 4 5 6 7 8 9 10
A 44 80 76 48 52 72 72 51 60 54
B 48 75 54 60 63 69 72 51 57 66
Find out who is better in studies and if coefficient is the criteria for awarding a prize
who should get the price?
Notes Solution:
X d = x - A d2
where, A = 60
44 -16 256
80 20 400
76 16 256
48 -12 144
52 -8 64
72 12 144
72 12 144
51 -9 81
60 0 0
54 -6 36
2
x = 609 d = 9 d = 1525
X 609
X = = = 60.9
N 10
2 2
d2 d 1525 9
= = = 152 .5 0.81
n n 10 10
X d = x - A d2
where, A = 60
48 -12 144
75 15 225
54 -6 36
60 0 0
63 3 9
69 9 81
72 12 144
51 -9 81
57 -3 9
66 6 36
2
X = 615 d = 15 d = 765
x 615 Notes
X = = = 61.5 marks
N 10
2
d2 d
=
n n
2
765 15
= = 76.5 2.25 = 74.25 = 8.617 marks
10 10
8.617
Co-efficient of variation = x 100 = x 100 = 14.01 %
X 61 .5
Here, co-efficient of variation is less for student ‘B’. So, ‘B’ is more consistent than
‘A’ and if prizs is based on consistency criteria, ‘B’ should get the prize.
Illustration - 5
Solution:
XA
Class interval X f d d2 fd fd2
20
10 - 30 20 14 -3 9 - 42 126
30 - 50 40 59 -2 4 - 118 236
50 - 70 60 101 -1 1 - 101 101
70 - 90 80 61 0 0 0 0
90 - 110 100 28 1 1 28 28
110 - 130 120 17 2 4 34 68
130 - 150 140 4 3 9 12 36
x = 560 n = 284 d = 0 d2 = 28 fd = -187 fd2 = 595
fd
x = A n i
187 3740
= 80 + x 20 = 80 - = 80 - 13.17 = 66.83
284 284
2 2
fd2 fd 595 187
Standard deviation ( ) = c x 20
n n 284 284
Illustration - 6
The following table gives the age distribution of boys and girls in a school. Find which
of the two groups is more variable in age:
Age: 10 11 12 13 14 15
No. of Boys: 11 14 14 10 8 5
No. of Girls: 13 15 12 9 5 3
Solution:
5
Boys = 12 + = 12 + 0.08 = 12.08
62
13
Girls = 12 + = 12 - 0.23 = 11.77
57
2
fd2 fd
SD ( ) =
N N
2
145 5
Boys = = 2.339 0.0065 2.3326 = 1.527
62 62
2
123 13
Girls = 2.158 0.052 2.106 = 1.451
57 57
CV = x 100
X
1.52
Boys = x 100 = 12.58%
12.08
1.45 Notes
Girls = x 100 = 12.32%
11.77
Boys are more variable in age since their CV is higher.
Illustration - 7
The following information is related to the marks scored in a test by girls section
and boys section in a school. From this, you are required to find out:
i) Which section scores more marks in an average?
ii) Which section is more consistent in scoring?
Marks: 0-10 10-20 20-30 30-40 40-50
No. of students
Boys section: 9 13 20 10 8
Girls section: 5 12 24 12 7
Solution:
X 25
Marks X Boys (X) Girls (Y)
10
Mid value d d2 f fd fd’2 f fd’ fd2
Calculation of Mean:
fd' 5
XB = A + x i = 25 + x 10 = 25 – 0.83 = 24.17
n 60
fd' 4
Ya = A + n
x i = 25 +
60
x 10 = 25 + 0.67 = 25.67
B 12 .3
CV = x 100 = x 100 = 50.89%
B 24 .17
2 2
fd' 2 fd' 72 4
a = x i = x 10
N N 60 60
= 1.093 x 10 = 10.93
a 10 .93
CV = x 100 = x 100 = 42.57%
Ya 25 .67
(i) Girls section scores more marks, because the average is more.
(ii) Boys section is more consistent because the CV is more of boys section.
Illustration - 8
Standard Deviation 10 11
Solution:
Batsman A Batsman B
Given No.of innings played 10 10
Average run scored x 45.5 52.5
Standard Deviation ( ) 10 11
Find out:
A) Who is better run getter?
Total run = No. of innings x Average score
For A = 10 x 45.5 = 455.
For B = 10 x 52.5 = 525
Batsman B is more run getter.
B) Who is consistent batsman? Use co-efficient of variation.
Batsman A
SD 10
CV = = x 100 = x 100 = 21.97%
Mean x 45.5
Batsman B
11
CV = x 100 = x 100 = 20.95%
x 52.5
Since coefficient of variation is more in case of batsman A, hence batsman B is
a more consistent batsman.
Amity Directorate of Distance and Online Education
Summary Statistics 87
Illustration - 9 Notes
The following are some of the particulars of the distribution of weights of boys and
girls in a class.
Boys Girls
Number 100 50
Mean weight 60 kgs 45 kgs
Variance 9 4
i) Find the Standard Deviation ii) Which of the two distributions is more variable?
Solution:
i) Standard Deviation = Variance
SD for Boys = 9 3
SD for Girls = 4 = 2
ii) Compute co-efficient of variation:
2
CV for Girls = 100 4.44%
45
Since, Co-efficient of variation for boys is more than Girls, Boys are more variable.
Illustration - 10
X Ltd. is actively considering the following two mutually exclusive projects for
adoption.
Year Project (X) Project (Y)
Cash profit (` in lakhs) Cash profit (` in lakhs)
1 10 5
2 5 25
3 20 45
4 40 30
5 60 30
Which is the most risky project (Use co-efficient of variation)
Solution:
X d=X- X d2
10 - 17 289
5 - 22 484
Notes 20 -7 49
40 13 169
60 33 1089
135 2
d = 0 d = 2080
X 135
X 27
N 5
2 2
d 2 d 2,080 0
SD of X = = = 416 20.4
n n 5 135
SD 20.4
CV for X = 100 = 100 75.54%
X 27
Y d=Y- Y d2
5 -22 484
25 -2 4
45 18 324
30 3 9
30 3 9
135 2
d = 0 d = 830
135
Y = 27
5
2
d 2 d 830 0 830
SD for Y = = = 0 166 12.88
n n 5 5 5
SD 12.88
CV for Y = 100 100 = 47.7%
Y 27
Since CV for X is more than CV of Y Project X is most risky.
Illustration - 11
Life(No. of Years): 0 - 2 2 - 4 4 - 6 6 - 8 8 - 10 10 - 12
Model A: 5 16 13 7 5 4
Model B: 2 7 12 19 9 1
a) Find the average life of each model.
b) Which model has great uniformity of life?
x 5 x 5
d =
2 2
Amity Directorate of Distance and Online Education
Summary Statistics 89
fd
xA = A + x i Where, A = 5, i = 2
n
3 250 6 256
= 5 + x 2 = = = 5.12
50 50 50
fd 29
xB = A + x i = 5 + x 2
n 50
250 58 308
= = = 6.16
50 50
2
fd 2 fd
A = xi
n n
2
649 3
= x2 = 12.98 0.0036 x 2
50 50
2
fd 2 fd
B = xi
n n
2
759 29
= x2 = 15.18 0.3364 x 2
50 50
C.V = x 100
x
7.2
C.V. of A = x 100 = 140.6%
5.12
Notes B 7.7
C.V. of B = y x 100 = x 100
6.16
= 125%
Model B has greater uniformity of life than model A.
2.12 Summary
Measures of central tendency is a single value which can be considered as
representative of a set of observations and around which the observations can be
considered as Centered is called an ’Average’ (or average value) or a Center of location.
An average is described as a measure of central tendency as it is more or less a
central value around which various values cluster. In the world of CROXTON and COWDEN
“an average is a single value within the range of the data that is used to represent all
of the values in the series.
Median is defined as the value of that item which divides the series into two equal
halves, one half contains all values less than (or equal to) it and the other half containing
all values greater than (or equal to) it. It is also defined as the “central value of the variable.
Mode is derived from the French word “1a mode” meaning fashion. So it can be
regarded as the most fashionable item in the series or the group.
The terms dispersion is used in two Senses. First, it means that all the items in
the group are not of the same value. They differ from one another in size. There is no
uniformity in size. Second, dispersion is used to indicate the measure of differences of
the size of items in the group from their average thus, a measure of deviations of items
from there average is called “the measure of dispersion.
Range is a measure of dispersion which gives the difference between the highest
and the lowest value in the series. The difference between the two extreme values is called
the range.
Mean deviation is the average amount of variations of the items in a distribution from
either the mean or the median or the mode, ignoring the signs of these deviations. It is
concerned with the extent to which the values are dispersed about the mean or the median
or the mode. In aggregating the deviation ignoring the negative sign.
Mode: is defined as the value of the variable which occurs most frequently in Notes
a distribution. In other words it as the most frequent size of item in a series.
Absolute measures: The dispersion results are expressed in terms of the
amount of variation i.e., in original units are called absolute measures, for
example range, mean deviation, standard deviation etc.
Relative measures: The dispersion results are expressed in terms of the
degree of variation i.e., ratios or percentages are called relative measures, for
example the coefficient of range, the coefficient mean deviation, the co-efficient
of variation etc.
SD: Standard deviation is defined as the Square root of the mean of the Squares
of deviations from the mean.
Notes 4. Aczel A.D. and Sounderpandian J., “Complete Business Statistics”, 6th edition,
Tata McGraw Hill Publishing Company Ltd., New Delhi, 2012.
5. Anderson D.R., Sweeney D.J. and Williams T.A., Statistics for business and
economics, 11th edition, Thomson (South – Western) Asia, Singapore, 2012.
2.19 Bibliography
1. Srivastava V. K. etal – Quantitative Techniques for Managerial Decision Making,
Wiley Eastern Ltd
2. Richard, I.Levin and Charles A.Kirkpatrick – Quantitative Approaches to
Management, McGraw Hill, Kogakusha Ltd.
3. Prem.S.Mann, Introductory Statistics, 7th Edition, Wiley India, 2016.
4. Aczel A.D. and Sounderpandian J., “Complete Business Statistics”, 6th edition,
Tata McGraw Hill Publishing Company Ltd., New Delhi, 2012.
5. Anderson D.R., Sweeney D.J. and Williams T.A., Statistics for business and
economics, 11th edition, Thomson (South – Western) Asia, Singapore, 2012.
6. Budnik, Frank S Dennis Mcleaavey, Richard Mojena – Principles of Operation
Research - AIT BS New Delhi.
7. Sharma J K – Operation Research- theory and applications-Mc Millan,New Delhi
8. Kalavathy S. – Operation Research – Vikas Pub Co
9. Gould F J – Introduction to Management Science – Englewood Cliffs N J Prentice
Hall.
10. Naray J K, Operation Research, theory and applications – Mc Millan, New Dehi.
11. Taha Hamdy, Operations Research, Prentice Hall of India
12. Tulasian: Quantitative Techniques: Pearson Ed.
13. Vohr.N.D. Quantitative Techniques in Management, TMH.
11. Stevenson W.D, Introduction to Management Science, TMH.