# Statistical methods

Pareto diagrams and dot diagrams: It is essential to collect data to provide the vital information necessary to solve engineering problems. Graphical illustration is an effective tool to describe the information. Pareto diagrams and dot diagrams fall into this category. Example 1: A computer-controlled lathe whose performance was below par, workers recorded the following causes and their frequencies. Power fluctuations 6 Controller not stable 22 Operator error 13 Worn tool not replaced 2 Other 5 1.

The data is presented as a special case of bar chart called a Pareto diagram shown in Fig.1. This diagram shows Pareto’s empirical law that any assortment of events consists of a few major and many minor elements. Typically, two or three elements will account for more than half of the total frequency.

The figure visually emphasizes the importance of reducing the frequency of controller misbehavior. As a second step toward improvement of the process, data were collected on the deviations of cutting speed from the target value set by the controller. The seven observed values of (cutting speed)-(target) 3 6 -2 4 7 4 3 are plotted as a dot diagram shown in Fig.2. The dot diagram visually summarizes the information that the lathe is, generally, running fast.

It helps to develop efficient experimental designs and methods for identifying primary causal factors that contribute to the variability in a response such as cutting speed.

2. the height of rectangles represent external between successive boundaries. His histogram displayed in Fig. After some thought he collected the sample of pellets used for grinding. What does the histogram reveal? .3. The grinding action was produced by pellets. Example 2: A histogram reveals the solution to a grinding operation problem. and measured their diameters. took them home. The histogram of a frequency distribution is constructed of adjacent rectangles. Most common form is the histogram. Frequency distributions: Properties of frequency distributions relating to their steps are best exhibited by means of graphs. spread them out of his kitchen table. A metallurgical engineer was experiencing trouble with a grinding operation.

By getting his supplier to do a better sort. . so all the pellets would be essentially from the first group. the engineer completely solved his problem.Solution: The histogram exhibits two distinct peaks. one for a group of pellets whose diameters are centered near 25 and the other concerned near 40.

(i. . (b) Median: It is a descriptive measure of the centre. or location of a set of data. Descriptive Measures: (a) Mean: Mean is the average defined by x= ∑ xi i =1 n n (1) To emphasize that it is based on a set of observation. it is often referred as Sample mean x .) . It is used to eliminate the effect of extreme (very large or very small) values. The median of n observations can be defined loosely as the middle most value when the data is arranged to size.3.e.

4.17. and 15. Solution: The mean is 11 + 9 + 17 + 19 + 4 + 15 x = 12.19. Find the mean and the median. The daily numbers for six days were 11.9.n +1 2 average of if n is even observation if n is odd. n n +1 + 2 2 Example 3: Calculation of the sample median with even sample size An engineering group receives email requests for technical information from sales and service persons.5 6 requests .

and. ordering the data from the smallest to largest 4 9 11 15 17 19    the median. (c)Sample Variance ( s 2 ): It is the average of the squared deviations from the mean x . s2 = ∑( x n i =1 i −x ) 2 (2) n −1 There are (n-1) independent deviations xi − x ( ) . the mean of the third and fourth largest values. . is 13 requests.

and positioning the tools) for cutting 6 parts on an engine lathe are 0.8 minutes.0.6.6 + 1. 1.9 + 1. 2 0.0 + 0. 0.2 + 0. Solution: First we calculate the mean: x 0.9.85 6 Then we set up the work required the following table: ∑( x − x) i 2 to find in . Calculate s .6 + 0. setting.8 = 0.Example 4: Calculation of sample variance The delay times (handling.6. and 0. 1.2.

2750 by (6 – 1) = 5 to obtain 0.We divide 0.055 (min ute) s 5 2 .2750 2 = = 0.

Solution: From the previous example. s 2 = 0. calculate s... is in wrong limits (minutes)2.055 .055 minutes . Hence. Take the square root and get = s = 0.. x is defined as the square root 1 2 n of their variance. standard deviation of n observations x .s2 (d) Standard deviation: In the above example.23 0. x ... s= ∑( x − x) n i =1 i 2 (3) n −1 Example 5: Calculation of sample standard deviation With reference to the previous example.

they measure the actual amount of variation in a set of data. the coefficient of variation. which gives the standard deviation as a percentage of the mean. (e)Coefficient of variation: s V = . that is. it is generally desirable to use a measure of relative variation.100 x (4) .The standard deviation and the variance are measures of absolute variation. To compare the variation in several sets of data. for instance. and they depend on the scale of measurement.

92 .92 mm and a standard deviation of 0.100 3.Example 6: The coefficient of variation for comparing relative preciseness Measurements made with one micrometer of the diameter of a ball bearing have a mean of 3.015 = V = 0. Which of these two measuring instruments is relatively more precise? Solution: For the first micrometer the coefficient of variation is 0. whereas measurements made with another micrometer of the unstretched length of a spring have a mean of 1.38% .54 inches and a standard deviation of 0.015 mm.008 inch.

.008 = = 0..52% V ..(n − r + 1)(n − r )! n! = (n − r )! (n − r )! (5) .And for the second micrometer the coefficient of variation is 0.54 Thus.100 1. 4.. Permutations and Combinations: (a) Permutations: The number permutations of r objects selected from a set of n distinct objects is n r P n(n − 1)(n − 2). the measurements made with the first micrometer are relatively more precise...

8! P4 = = = 11. second.11. In how many ways can this mechanism be assembled by placing the 5 chips in the 5 positions within the controller? . and fourth choice among 12 firms leasing construction equipment? Solution: For n = 12 and r = 4. the first formula yields 12! 12! 12.9.10. third.880 12 = (12 − 4)! 8! 8! Example 8: The number of ways to assemble chips in a controller An electronic controlling mechanism requires 5 identical memory chips.Example 7: Evaluating a permutation In how many different ways can one make a first.

4. the first formula yields = 5.Solution: For n = 5 and r = 5.3.2.1 120 = 5P 5 And the second formula yields 5! 5! = = = 5! 120 = 5P 5 ( 5 − 5)! 0! .

..(n − r + 1) r= r!   (6a) or n n! r=   r !(n − r )! (6b) ..(b)Combinations: Combination of n objects taken r at a time and denoted by n Cr or n r    n  n(n − 1)(n − 2)..

Example 9: Evaluating a combination In how many ways different ways can 3 of 20 laboratory assistants be chosen to assist with an experiment? Solution: For n= 20 and r = 3.2.140 3 3!   Example 10: Selection of machines for an experiment A calibration study needs to be conducted to see if the readings on 15 test machines are giving similar results.1   . the first formula for n  r  yields    20  20. In how many ways can 3 of the 15 be selected for the initial investigation? Solution: 15  15.14.18 = = 1.13 = = 455 ways 3 3.19.

By 3  the multiplication rule. That is.Note that selecting which 3 machines to use is the same as selecting which 12 not to include.764 ways 7  2  = 21   . the whole selection can be made in 21 * 84 = 1. according to the second formula 15  15! 15! 15  = = = 12  12!3! 3!12!  3      Example 11: The number of choices of new researchers In how many different ways can the director of a research laboratory choose 2 chemists from among 7 applicants and 3 physicists from among 9 applicants? Solution: The 2 chemists can be chosen in ways 9 and the 3 physicists can be chosen in   = 84 ways.

Probability: If there are n equally likely possibilities. What is the probability of drawing an ace from a wellshuffled deck of 52 playing cards? Solution: There are s = 4 aces among the n = 52 cards.” then the probability of a “success” is given by s . so we get s 4 1 = = n 52 13 . of which one must occur and s are regarded as favorable. n Example 12: Well-shuffled cards are equally likely to be selected.5. or as a “success.

42 =    3*680 2.040 8 = 4. s = =  1  3  2. so n = 4.040.845   s It follows that the probability is = n or approximately 0.845 19 . each tire has the same chance of being selected).Example 13: Random selection results in the equally likely case If 3 of 20 tires in storage are defective and 4 of them are randomly chosen for inspection (that is.845. or  20   4  = 4. what is the probability that only one of the defective tires will be included? Solution: There are equally likely ways of choosing 4 of 20 tires. The number of favorable outcomes is the number of ways in which one of the defective tires and three of the nondefective tires can be  3 17  selected.

294 = 0.(a)The frequency interpretation of probability The probability of an event (or outcome) is the proportion of times the event would occur in a long run of repeated experiments. and we use this figure as an estimate of the probability. were able to withstand the thermal shock. what is the probability that any one untested insulator will be able to withstand the thermal shock? Solution: Among the insulators tested.98 300 . Example 14: Long-run relative frequency approximation of probability If records show that 294 of 300 ceramic insulators tested were able to withstand a certain thermal shock.

= The first axioms states that probabilities are real numbers on the interval from 0 to 1. The second axiom states that the sample space as a whole is assigned a probability of 1 and this expresses the idea that the probability of a certain event. is equal to 1. an event which must happen.(b) Axioms of Probability: Axiom 1 Axiom 2 Axiom 3 0 ≤ P ( A) ≤ 1 for each event A in S. then P ( A ∪ B ) P( A) + P( B). (7a) (7b) (7c) P( S ) = 1 If A and B are mutually exclusive events in S. . The third axiom states that probability functions must be additive.

.

40 + 0. find the probability that a lawn mower will be rated easy to operate or having high average cost of repairs.12 = 0.58 .30 and P ( E1= 0.30 − 0. namely P ( E1 ∪ C1 ) .(c) General addition rule of probability Theorem: If A and B are any events in S.12 we substitute into the formula of above theorem and get P ( E1 ∩ C1 ) = 0.40. = 0. = 0. P ( E1 ) P ( C1 ) ∩ C1 ) Solution: Given. then P ( A ∪ B ) P( A) + P( B) − P ( A ∩ B ) = (8) Example 15: Using the general addition rule for probability With reference to the lawn-mower-rating example.

0.29 that.29 = 0. or both. If the probabilities are 0.87 + 0.36 − 0. the P ( A ∩ B) P AB = P( B) ( ) (9) . what is the probability that a car will require one or the other or both kinds of repairs under the warranty? Solution: Substituting these given values into the formula of above theorem. and 0. while under warranty. a new car will require repairs on the engine.87.Example 16: The probability of requiring repair under warranty. we get 0. drive train.94 (d) Conditional Probability: If A and B are any events in S and conditional probability of A given B is P( B) ≠ 0 .36.

18.81 and the probability that it will have high fidelity and high selectivity is 0.81 9 and substitution into the formula yields ( ) . what is the probability that a system with high fidelity will also have high selectivity? Solution: If A is the event that a communication system has high selectivity and B is the event that it has high fidelity.81 and = 0.18 2 P AB = = 0.18.Example 17: Calculating a conditional probability If the probability that a communication system will have high fidelity is 0. we have = 0. P ( B) P ( A ∩ B) 0.

30 ( ) . P ( E1 ∩ C1 ) and P ( C1 ) substitution into the formula for a conditional probability yields 0.12 = 0. for which the probabilities of the individual outcomes are given in fig 1.12 P E1C1 = = 0. use the results obtained to find P ( E1 C1 ) Solution: Since we had = 0.40 0.Example 18: The conditional probability that a lawn mover is easy to operate given that repairs are costly Referring to the lawn-mower-rating example.30.

P( B A) if P ( A) ≠ 0 P ( B ).(e) General multiplication rule of probability Theorem: If A and B are any events in S. If 12 workers favor the new regulations and the other 8 are against them. what is the probability that both of the workers chosen by the supervisor will be against the new safety regulations? .P ( A B ) if P ( B ) ≠ 0 (10) Example 19: Using the general multiplication rule of probability The supervisor of a group of 20 construction workers wants to get the opinion of 2 of them ( to be selected at random) about certain new safety regulations. then P ( A ∩ B ) P( A).

Solution: Assuming equal probabilities for each selection (which is what we mean by the selections being random). the probability that the first worker selected will be against 8 the new safety regulations is . 20 19 95 19 (f) Special product rule of probability Two events A and B are independent events if and only if P ( A ∩ B ) =A).P( B) P( (11) . = . and the probability that 20 the second worker selected will be against the new safety regulations given that the first one is against them is 7 Thus. the desired probability is 8 7 14 .

Example 20: The outcome to unrelated parts of an experiment can be treated as independent What is the probability of getting two heads in two flips of a balanced coin? Solution: Since the probability of heads is for each flip 2 and the two flips are independent the probability is 1 1 1 1 . = . 2 2 4 Example 21: Independence and selection with and without replacement Two cards are drawn at random from an ordinary deck of 52 playing cards. What is the probability of getting two aces if .

we get 4 3 1 52 51 . = . . = 221 .(a) the first card is replaced before the second card is drawn. . Note that 221 52 52 so independence is violated when the sampling is without replacement. 52 52 169 (b) Since there are only three aces among the 51 cards that remain after one ace has been removed from the deck. we get 4 4 1 . (b) The first card is not replaced before the second card is drawn? Solution: (a) Since there are four aces among the 52 cards. 1 4 4 ≠ .

65 )( 0. If assign = 0.8 and P ( B ) 0.65.7.24.40 ) the two events are not independent.P ( D ) (= 0.40 and P ( C ∩ D ) P (C ) = C and D independent? are the events Solution: Since P ( C ) . P ( D ) 0. Example 23: Assigning probability by the special product rule Let A be the event that raw material is available when needed and B be the event that the machining time is less than 1 hour.26 and not 0.Example 22: Checking if two events are independent under an assigned probability If = 0. P ( A) = probability to the event A ∩ B . = 0.

. = . 2 9 6 . we invoke independence and make the assignment P ( A = P ( A ) . .8) = 0.Solution: Since the events A and B concern unrelated steps in the manufacturing process.7 ) ( 0. ( 0.= ∩ B) P ( B) .56 Example 24: The extended special product rule of probability What is the probability of not rolling any 6’s in four rolls of a balanced die? Solution: The probability is 5 5 5 5 6 2 5 . 6 6 6 6 1.

6. then P ( Br A ) = P ( Br ) ....... . Bn are mutually exclusive events of which one must occur..P( A Bi ) i =1 n (12) (b)Bayes’ Theorem: If B1 . B2 ... then P ( A ) = ∑ P ( Bi ).. Bn are mutually exclusive events Theorem: If of which one must occur. n..P( A Bi ) i =1 n (13) for r = 1...P ( A Br ) ∑ P( Bi ).. B2 . 2.. Bayes’ Theorem: (a)Rule of elimination: B1 .

.

who services 60% of the breakdowns. who services 15% of the breakdowns. makes an incomplete repair 1 time in 20. what is the probability that this initial repair was made by Jagat? .Example 25: Using Bayes’ Theorem Four technicians regularly make repairs when breakdowns occur on an automated production line. makes an incomplete repair 1 time in 10. Tyagarajan. who services 20% of the breakdowns. Guna. and Pandyan. makes an incomplete repair 1 time in 10. who services 5% of the breakdowns. For the next problem with the production line diagnosed as being due to an initial repair that was incomplete. makes an incomplete repair 1 time in 20. Jagat.

05) and it is of interest to note that although Jagat makes an incomplete repair only 1 out of 20 times... a2 .. If the probabilities of obtaining the amounts p1 .10) + (0...60)(0.Solution: Substituting the various probabilities into the formula of Bayes’ Theorem.... Mathematical expectation of Decision making.. we get P B1 A ( ) (0..05)(0.20)(0....114 (0.05) = 0....10) + (0.... 7.15)(0. more than 11% of the incomplete repairs are his responsibility.. and pk . p2 . or ak are mathematical expectation is (14) E = a1 p1 + a2 p2 + . namely. + ak pk .05) + (0. 5% of the breakdowns.20)(0. then the a1 .

what is the distributor’s expected profit per item? . If 70% of such items are shipped in perfect condition and arrive on time.Example 26: Mathematical expectation of net profit A distributor makes a profit of Rs 200 on an item if it is shipped from the factory in perfect condition and arrives on time. 10% are shipped in perfect condition but do not arrive on time and 20 % are not shipped in perfect condition. and by Rs 120 regardless of whether it arrives on time if it is not shipped from the factory in perfect condition. but it is reduced by Rs 20 if it does not arrive on time.

20) = Rs174 The result is the sum of the products obtained by multiplying each amount by the corresponding proportion or probability. the Rs 180 profit 10 % of the time.Solution: We can argue that the distributor will make the Rs 200 profit 70 % of the time.10) + 80(0. so that the average profit per item ( the expected profit) is 200(0.70) + 180(0. and the Rs 80 profit 20 % of the time. .

They are denoted with capital letters X. Discrete random variables can take only a finite number.5.8.6 . Y and so on to distinguish them from their possible values given in lower case. 2.Probability Distributions: Random variables: They are functions defined over the elements of a sample space. 1 f ( x) = 6 for x = 1.3. Random variables are usually classified according to the number of values which they can assume. 4. The function f(x) = P(X=x) which assigns probability to each possible outcome x that is called the probability distribution. or a countable infinity of values.

Gives the probability distribution for the number of points we roll with a balanced die.1.e) f ( x) ≥ 0 for all x ∑x f ( x) = 1 and all Example 27: Checking for nonnegativity and total probability equals one Check whether the following can serve as probability distributions: x−2 f ( x) = (a) for x = 1.4 .2.4 2 (b) x h( x ) = 25 2 for x = 0.2.3.3. Since the values of probability distributions are probabilities and one value of a random variable must always occur (i.

(ii) The probability that 9 of 10 VCRs will run at least 1000hours .Solution: (a) This function cannot serve as a probability distribution because f(1) is negative (b) The function cannot serve as a probability distribution because the sum of the five probabilities is 6 and 5 not 1.Binomial Distribution: Many statistical problems deal with the situations referred to as repeated trials. 9. For example we may want to know (i) The probability that one of five rivets will rupture in a tensile test.

(1-p): Probability of failure on any one trial. 4. Trials satisfying these assumptions are referred to as Bernoulli trials. There are only two possible outcomes for each trial. Let X: be the random variable that equals the number of successes in n trials. There are n trials. 3. where n is a constant.In determining the probability the following assumptions are made 1. The n trials are independent. . 2. The probability of a success is the same for each trial. p: Probability of success on any one trial.

the values of the probabilities are the successive terms of binomial expansion of [ p + (1 − p ) ]n .n x () .……..…. and we arrive at () b(= x. Actually.2. the preceding equation defines a family of probability distributions with each member characterized by a given value of the parameter p and the number of trials n.. n.1.2. () n p x (1 − p ) n− x for x = 0.1. the combinatorial quantities n are referred to as binomial x coefficients. for the same reason. the number of combinations of x objects selected from a set of n objects.The probability of getting x success and (n-x) failures in some specific order is p x (1 − p ) n− x The number of ways in n which x trials can be selected is x . p ) This probability distributions is called the binomial distribution because for x = 0. and n.

and p=0. Accordingly.60 4 (1 − 0.Example 28: Evaluating binomial probabilities It has been claimed that in 60% of all solar heat installations the utility bill is reduced by at least one-third.259 5− 4 ) 4 ( .60)= 0. n=5. (b) at least four of five installations? Solution: (a) Substituting x=4. we get b(4.0.5.60 into the formula for the binomial distribution.60) = () 5 0. what are the probabilities that the utility bill will be reduced by at least one-third in (a) four of five installations.

n=5.078 = 0.0.60)= 0.5.0.078 5 −5 ) 5 ( b(4.60 5 (1 − 0.(b) Substituting x=5. and p=0.0.60 into the formula for the binomial distribution.337 .60) = 0.5.259 + 0.5. we get b(5.60) = and the answer is () 5 0.60) + b(4.