Course Material BM QT 2019 PDF

XLRI, Jamshedpur PGDM (BM) 2019
QUANTITATIVE TECHNIQUES-I
Instructor: Apratim Guha

Email: apratim@xlri.ac.in
Phone: +91 (657) 665-3452
Course Objective
The purpose of the course is to introduce you to the management of uncertainty in managerial
decisions. In this course, we shall discuss situations where uncertainty plays a role in the
decisions involved and where the assessment of uncertainty becomes imperative. We shall also
go over technical aspects like axioms of probability, probability computations, probability
distributions, summary measures of probability distributions etc., along with a brief
discussion of decision theory.
The technical part of the course is being developed through a series of problems. It may seem
to you that many of the problems can be intuitively solved. While developing your intuition is
extremely important, you should also try to see whether or not you can obtain a rigorous
framework for handling such problems. This may appear cumbersome in the beginning.
However, if you follow this, you would develop skills to deal with more complex situations. The
concepts are intuitive, but to master them you need systematic study. You would get all the
help required in this process of learning.
The text book will be an important tool in developing your intended skillset. You would be
expected to read and understand the suggested parts of the text on your own, and develop
your skill to solve the problems given in the book, and in class.
Please note that the topic of decision theory is not covered in the text book. For that topic a
separate handout will be provided.
Readings
Textbook:
Probability: Jim Pitman. Springer.
Suggested Additional Reading:

1. A First Course in Probability, 9th Edition: Sheldon M. Ross. Pearson.
2. An Introduction to Probability Theory and its Applications, Volume 1, 3 rd Edition: William
Feller. Wiley.
3. Introduction to Management Science, 6th Edition: F. S. Hillier and M. S. Hillier, McGraw
Hill. (Read Ch. 9 only)
4. Statistics for Business: Decision Making and Analysis, 2 nd Edition: Robert A. Stine and
Dean Foster, Pearson.
1
Evaluation Components (See Session Details below for the definition of “Parts”)
Quiz on topic of Parts I and II 30%
Quiz on topics of Parts III and IV 30%
End term (all topics) 40%
Grading system
Below 15%: F, at least 15% but below 20%: D, at least 20% but below 25%: D+. Grades
between A+ to C will be awarded to the remaining students in the following manner:
i) Top 30% of the students will receive grades of A or A+. Students scoring 90% or above are
guaranteed to receive a grade of A+.
ii) At least a further 45% of the students will receive grades of B or B+. Students in the bottom
25% may also receive a grade of B provided they have scored at least 60%.
iii) The remaining students will receive grades of C or C+.
Important Notes
1) For attendance deficiency, grades will be downgraded as per institute rules.
2) You are not allowed to come late to the class. Anyone arriving late will be turned away and
marked absent.
3) Academic indiscipline will be dealt with severely as per institute rules.
4) No solicitation for grades will be entertained.
2
Session Details
Sessions Topics Reading

Part I: Theory of Probability
1-5 a) Different approaches to probability Ch. 1 of text
b) Computation of probability
c) Conditional probability and independence
d) Bayes’ rule and consequences
e) Sequence of events
Part II: Univariate Discrete Distributions
6-9 a) Random variables Ch.s 2 and 3 of text
b) Discrete random variables: concepts of p.m.f. and c.d.f. (skip Sections 2.2,
c) Concepts of expectation, variance and standard deviation 2.3 and 3.3)
d) Standard discrete random variables: binomial, Poisson,
geometric, negative binomial and hypergeometric
Part III: Joint and Conditional Distributions (Discrete Variables Only)
10-12 a) Joint, marginal & conditional distributions. Ch. 6 of text (skip
b) Multinomial distribution. Sections 6.3 and 6.5)
c) Expectation and variance of sum of random variables.
d) Covariance.
Part IV: Univariate Continuous Distributions
13-15 a) Continuous random variables: concepts of density, c.d.f. Ch. 4 of text
and quantiles
b) Standard continuous random variables: uniform, normal,
exponential and gamma
Part V: Central Limit Theorem
16-17 a) Idea of random sampling. Sections 2.2, 2.3 and
b) Central limit theorem and applications. 3.3 of text
Part VI: Decision Theory
18-20 a) Decisions under uncertainty To be provided in
b) Sequential decision making: decision tree class
c) Expected value of perfect information and expected value
of sample information
3
Practice problems for Parts I-V. For practice problems for Part VI, refer to the problem sets at the
end of the handout sections.
1. Is anything wrong with the following argument? 20% of the Indians are senior citizens, 45% of the
Indians are women. So the proportion of women senior citizens is 45% of 20% = 9%.
2. Two dice are thrown n times in succession. What is the probability of obtaining double six at least
once?
3. If n accidents have taken place in Jamshedpur during the first N days of the year 2019, what is
the probability that on January 1st, exactly b accidents took place in Jamshedpur?
4. Each of k urns contains n distinct balls labeled from 1 to n. One ball is drawn from every urn.
What is the probability that m is the greatest label drawn?
5. In a psychology experiment, each subject is presented 3 ordinary cards, face down. The subject
takes one of those cards. The subject also takes one card at random from a separate, full, deck of 52
cards. If the two cards are from the same suit (Heart/Diamond/Club/Spade), the subject wins a prize.
What is the chance of winning?
6. If A and B are two events such that A and B are mutually exclusive, P(A) > 0, P(B) >0, then can A
and B be independent? Justify your answer.
7. If A, B and C are three events such that P(A|B) = P(A) and P(A|C) = P(A) where P(A) > 0, then
are A, B and C mutually independent of each other? Justify your answer.
8. Consider families with two children. If one child of a family is a boy, what is the probability that
the other child is a girl?
9. An urn contains a white and b black balls. If m + n balls are chosen at random, find the probability
that m of them are white and n are black balls.
10. From a class of m boys and n girls, k (< m+n) students are randomly selected to volunteer for
school sports. We do not know their gender. Now one more student from the remaining students in
the class is randomly selected. Find the probability that it is a girl.
11. According to a research study, the incidence rate of HIV in India is 0.4% for a certain section of
the population. A Clinical test in India is 95% accurate in detecting HIV. i.e., if there is actually HIV,
the test will be correctly detect it 95% of the times. If there is no HIV, the test will again be correct
in 95% of cases. A person from this section of the population undergoes a test and the test says he
has HIV.
a) What is the probability that he really has the disease?
b) A second independent test that has similar accuracy also comes out positive. Now, what is the
probability that he has disease? (Such an update of probability based on additional information is
referred to as "Bayesian Update")
1
12. A die is thrown three times. Work out the following probabilities assuming I) the die is fair, II)
the die is biased with P(1) = 0.25, P(2) = P(3) = P(4) = P(5) = P (6) = 0.15:
a) the sum of the numbers shown on the three dice is even
b) the product of the numbers shown on the three dice is divisible by 4
c) the sum of the numbers shown on the three dice is even, given that their product is divisible by 4
13. In a factory, machines A, B and C manufacture 25, 35 and 40 percent of total production
respectively. Of their output 5, 4 and 2 percent are defective respectively. A product is drawn at
random from the produce and is found to be defective. What is the probability that it was
manufactured by machine A?
14. A production process involves three machines A, B and C, which produce 50%, 30% and 20%
respectively of the total output. Out of the items produced by machine A, 10% fail in a quality control
test. The corresponding figures for Machines B and C are 20% and 30% respectively. All items
passing the quality control test are directly acceptable. On the other hand, items failing in the quality
control test are further processed and thus 40%, 50% and 60% of them turn out to be marginally
acceptable, depending on whether they came from machines A, B and C respectively. For example,
out of the items that are produced by Machine A and that fail in the quality control test, 40%
eventually turn out to be marginally acceptable, and so on.
a) Find the unconditional probability that a randomly chosen item from the production process is
found to be directly acceptable.
b) Find the probability that a randomly chosen item from the production process turns out to be
marginally acceptable.
c) Given that a randomly chosen item from the production process has failed in the quality control
test, what is the conditional probability that it turns out to be marginally acceptable?
d) Given that a randomly chosen item from the production process has turned out to be marginally
acceptable, what is the conditional probability that it was produced by Machine A?
e) Given that a randomly chosen item was not produced by Machine B, what is the conditional
probability that it turns out to be marginally acceptable?
15. Scott Myers is a security analyst for a telecommunications firm called Webtalk. Although he is
optimistic about the firm’s future, he is concerned that its stock price will be hugely affected by the
condition of credit flow in the economy. He believes that the probability is 0.2 that credit flow will
improve significantly, 0.5 that it will improve only marginally and 0.3 that it would not improve at
all. He also estimates that the probability that the stock price of Webtalk will go up by at least 20%
is 0.9 with significant improvement in credit flow, 0.4 with marginal improvement in credit flow and
0.1 with no improvement in credit flow.
a) What is the unconditional probability that the stock price of Webtalk goes up by at least 20%?
b) Given that the stock price of Webtalk has not gone up by more than 20%, what is the probability
that there was no improvement in credit flow?
2
16. Mektek, a new company, is thinking about developing a smartphone. However, before they start
developing the smartphone, they want to make sure that it will make sense to invest on this. They
are planning to employ a market survey farm to sense the market. The following are the
considerations:
The market survey can predict 3 scenarios: high, medium or low demand. In a high demand
situation, Mektek makes a profit of Rs. 10,00,00,000 (10 Crores). In case of medium demand, they
make a profit of Rs. 1,00,00,000 (1 Crore), and in case of a low demand, they lose Rs. 2,00,00,000 (2
Crores).
The probabilities with which the market survey will predict high, medium or low demand are 40%,
20% and 40% respectively. The problem is that historically when such a survey had predicted high
demands, 40% of the time it were wrong, half of such cases in fact being that of low demand, and
rest of medium demand. Similarly, when such a survey predicted medium demand, it was correct
only 70% of the times, with rest of the cases being split equally between high and low demand. The
survey, however, has worked well in case when a low demand scenario was predicted; it was correct
90% of the times in such a case, the rest of the cases all being of medium demand.
a) What is the probability that Mektek will make a profit given that the market survey has predicted
a low demand scenario?
b) What is the (unconditional) probability that Mektek will make a loss?
c) What is the probability that Mektek will make a loss given that the market survey has not
predicted a low demand scenario?
d) If MekTek is risk-neutral, what should they do in case the predicted demand is i) high, ii) medium
or iii) low? What would have their optimal strategy been if the survey was not done?
17. Suppose A, B and C are mutually independent events and that P(A) = 0.5, P(B) = 0.8 and P(C) =
0.9. Find the probabilities that
a) All three events occur.
b) Exactly two of three events occur.
c) None of the events occurs.
18. Two six faced fair dice are thrown. Let Event A = Die 1 shows six, Event B = Die 2 shows six and
Event C = Both dice show the same face. Show that A, B, C are pairwise independent but not
mutually independent.
19. Consider families with 3 children. Let B denote boy and G denote girl. Assume that all 8
possibilities for the three children in order have equal probabilities. Define events A B and C as
follows: A= at least 2 boys, B= 1st child is a girl, C= 2nd child is a boy. Show that P(A ∩ B ∩ C) =
P(A) × P(B) × P(C) but A, B, C are not pairwise independent.
20. A machine has n components. It functions only if at least one component functions. All
components function independently and probability of any one component not functioning is p. What
is the probability that all components are functioning given that the machine is functioning?
3
21. A system has two components: A and B. The system functions as long as at least one component
functions. If both A and B are functional at the start of the day, then they fail independently during
the day with probability of failure for each component being 0.2. If exactly one of A and B is functional
at the start of the day, then the functional component fails during the day with probability 0. 4.
Answer the following questions assuming that both A and B were functional at the start of Monday.
a) What is the probability that the system is functional at the start of the day on Tuesday?
b) What is the probability that the system is functional at the start of the day on Wednesday?
c) What is the probability that the system is functional at the start of the day on Thursday given
that the system is functional at the start of day on Tuesday?
22. Consider the following system where gas is supposed to flow from A to B:
There are three valves in the system: V1, V2 and V3, each of which may develop faults, and hence
stop working, independently with probability p. Gas will flow from A to B if either both valves in the
pair (V1, V2) or the valve V3 or all three valves are functional.
a) What is the probability that gas is flowing from A to B?
b) Given that gas is flowing from A to B, what is the probability that V1 has developed a fault?
c) Given that gas is not flowing from A to B, what is the probability that V1 has not developed a
fault?
23. From an urn containing 3 white and 5 black balls, 4 balls are transferred into an empty urn.
From this urn 2 balls are taken and they both happen to be white. They are then replaced. What is
the probability that the third ball taken from the same urn will be white?
24. An urn has 3 black balls and 5 white balls. Each time I draw a ball. If it is black, I add 1 black
ball and 2 white balls. If it is white, I add 2 black balls and 1 white ball. Assume that the ball that
is originally drawn is also replaced along with the additional balls. In four successive draws, what is
the probability of getting a Black-White-Black-White in four successive draws?
25. Simpson's paradox, or the Yule–Simpson effect, is a paradox in which a trend that appears in
different groups of data disappears when these groups are combined, and the reverse trend appears
for the aggregate data. Consider the following example:
Abracadabra University is well-known for its bias against women. Last year 3000 applicants applied
to join the undergraduate programme of the university, among them 2000 were men and 1000
women. 100 women were shortlisted (10%), along with 300 men (15%). A clear case of sexual bias is
apparent. In fact, that has been the trend for years.
4
What, however, baffles the university authority is that they gave clear instruction to both of its two
schools, Arts and Science, to try to admit more women, and they did try to oblige. So what happened?
Let’s examine the admission offers last year:
Men Women
Arts 295 accepted/1900 applied 10 accepted/50 applied
Science 5 accepted/100 applied 90 accepted/950 applied
Compute and compare the proportion of men and women admitted to the Schools of Arts and Science:
i.e. compute
a) What is the probability that a random male applicant gets selected in the School of Arts?
b) What is the probability that a random female applicant gets selected in the School of Arts?
c) What is the probability that a random applicant gets selected in the School of Arts?
d) What is the probability that a random male applicant gets selected in the School of Science?
e) What is the probability that a random female applicant gets selected in the School of Science?
f) What is the probability that a random applicant gets selected in the School of Science?
Based on a)-f) above, can you explain what is going on? Is the criticism towards the university
justifiable? What is your take on this analysis?
26. Consider a random variable X with the following distribution:

X -3 -1 0 1 2 3 5 8
P(X=x) 0.1 0.2 0.15 0.2 0.1 0.15 0.05 0.05
a) P(X > 0),

b) P(X is even),
c) P(1≤ X ≤8),
d) P(X = -3 | X ≤ 0),
e) P(X ≥ 3 | X > 0),
f) E[X],
g) V[X].
27. Suppose that a school has 20 classes: 16 with 25 students in each, three with 100 students in
each and one with 300 students for a total of 1000 students.
a) What is the average class size?
b) Suppose a student is picked at random from the 1000 students. Let X= size of the class to which
(s)he belongs. What is the p.m.f of X?
c) What is E[X]?
d) Is it surprising that a) and c) are not equal? Can you define a random variable Y such that E[Y]
will give the answer in a)?
5
28. A gambling guide recommends the following ``winning strategyʹʹ to make money in the game of
roulette. It recommends that a gambler bet Rs.100 on red. If red appears, then the gambler should
take the money and quit. If he loses, then he should bet Rs.100 on red for the next two spins and
then quit. Note that P(red) = 9/19. Note that if betting Rs.100 means that you pay the casino Rs.100
to play; if you win you get back your Rs.100 plus another Rs.100, but if you lose then the casino keeps
your payment. Let X be the gambler’s winnings when he quits. Find P(X>0) and E(X) and comment
on the strategy.
29. According to a study conducted on eating habits of an adult population in a country, it is found
that 25% of males and 20% of females never eat breakfast. Suppose a sample of 5 men and 5 women
are chosen. Compute the probability that
a) At least 2 of the 10 never eat breakfast.
b) The number of women who eat breakfast is at least as much as the number of men who eat
breakfast.
c) What would have been the answer to (a) if both the percentage of men and women who did not eat
breakfast were equal to 20%?
30. Probability of hitting a target is 0.2 and 10 shots are fired independently.
a) What is the probability of never hitting the target in the ten attempts?
b) What is the probability of hitting the target in the 7th attempt for the first time? What about the
second time?
c) What is the probability of hitting the target at least twice in 10 attempts?
d) What is the probability that the target was hit at least twice in 10 attempts, given that it had
been hit at least once in 10 attempts?
e) Five more shots are fired, independently among themselves and independent of the previous
shots. What is the probability of at least two hits to the target in these 15 shots if i) the probability
of hitting remains 0.2 for these five shots, and ii) the probability of hitting the target in the last 5
shots is revised to 0.5 for the last five shots?
31. An airline always overbooks if there is demand. A particular plane has 180 seats and each ticket
cost Rs. 4000. The airline has sold 190 such tickets.
a) If the probability of an individual not showing up is 0.05, assuming independence, what is the
probability that the airline can accommodate all who show up? (Hint: Define r.v X = number of people
who show up out of 100. Express the probability in terms of X and compute.)
b) If the airline must return the ticket price, plus pay a penalty of Rs. 5000 to all who show up but
cannot be accommodated, what is the expected total penalty that the airline will have to pay? (Hint:
Create a new r.v. Y= penalty paid by airline. Express Y in terms of X. Since we know the distribution
of X, find the distribution of Y. i.e. identify the possible values of Y and the corresponding
probabilities.)
6
32. In a certain shop floor, a certain machine has 1% rate of producing defective items. The items are
packed in lots of 50. A customer will not accept a lot if it contains 3 or more defectives.
a) If it is known that a lot is not defective free, find the probability that it will be rejected by the
customer.
b) Find the probability that out of 10 lots, exactly 2 are rejected by the customer.
33. A graduating student keeps applying for a job until she gets an offer. Assume that she applies
for one job at a given time, waits for the result and then applies for the next job. The probability of
getting a job offer on an application is p.
a) If p = 0.25, what is the expected value and variance of the number of applications?
b) Let p = 0.25. Suppose she only has time to apply for at most four jobs. What is the probability that
she will get at least one job offer?
c) Suppose she only has time to apply for at most four jobs. What would be the minimum value of p
that would ensure at least a 95% chance of getting at least one job offer?
34. The number of breakdowns of a computer system in a month is believed to follow a Poisson
distribution. It has been consistently observed in the past that the average number of monthly break
downs is 1. Find the probability that this computer will work for 3 months (a) without any break
down (b) with exactly one break down.
35. Colour blindness occurs in 1% of a population. How large a random sample (with replacement)
should one draw from the population if the probability of it containing at least 1 colour blind person
is 95% or more? Use both the binomial and Poisson distributions to derive the required sample sizes.
36. A purchaser of electrical components buys them in lots of size 10. It is his policy to inspect three
components randomly chosen from the lot and to accept the lot only if all three are non-defective. If
30% of the lots have four defective components and 70% have only one, what proportion of lots will
the purchaser reject?
37. A random sample of size 3 is drawn without replacement from a lot of size 10, which contains 4
defective items. What is the probability that at least 1 of the 3 items drawn are defective?
38. You are interested in estimating the proportion of missing books in a library. You take the
catalogue and design two sampling plans:
i. Draw a random sample of size 10 of names with replacement from the catalogue. Then look them
up in the library to see how many of them are missing.
ii. Keep drawing a random item sequentially, with replacement, from the catalogue and check
whether the item is missing or not. Once you encounter two missing books, you stop the sampling.
If the true proportion of missing books = 0.1,
a) What are the expected number of books you will check in the two schemes?
b) What is the probability that you encounter no missing item in the first sampling scheme?
c) What is the probability that you will sample more than 10 items in the second sampling scheme?
7
39. Suppose a 6 faced die has 2 faces numbered 1, 3 faces numbered 2 and 1 face numbered 3. Suppose
the die is thrown independently 10 times and in each throw each face has an equal chance of showing
up.
a) What is the joint distribution of (X1, X2, X3) where Xi = number of times face i shows up?
b) What is the distribution of (X1 + X2)?
40. X and Y are random variables with the joint distribution as given in the table below:
X Values
Y values↓ -1 0 2 6
-2 1/9 1/27 1/27 1/9
1 2/9 0 1/9 1/9
3 0 0 1/9 4/27
a) Obtain the marginal distributions of X and Y.

b) Are X and Y independent?
c) Compute P(Y is even).
d) Compute P(XY is odd).
e) Compute E(X) and V(X).
f) Compute E(Y) and V(Y).
g) Compute Cov(X,Y) and Cor(X,Y).
h) Compute E(X|Y = j) for j = -2, 1, 3.
i) Let g(Y) = E(X|Y). Verify that E(E(X|Y)) = E(X).
41. Let X~Poisson(λ1) and Y~Poisson(λ2) be independent. Obtain the conditional distribution of
X|X+Y=n.
42. The number of customers arriving at a bank has a Poisson distribution with rate 10 per hour.
Each customer arrives independently of each other, and is either male with probability 0.6 or female
with probability 0.4. Let X = number of male customers arriving in an hour and Y = number of female
customers arriving at the same hour.
a) What is the joint distribution of (X,Y)?
b) Are X and Y independent?
c) What are the marginal distributions of X and Y?
43. A middle level executive of a multinational company in Mumbai receives several telephone calls
on his cell phone. According to him the calls arrive independently and are governed by a Poisson
distribution with an average of 8 calls per day. The calls originate either from known acquaintances
or from complete strangers in the ratio of 3:1 respectively. Answer the following questions.
a) What is the probability that the number of calls in a day is exactly 5?
b) What is the expected number of calls from strangers on any given day?
c) Given that there were 5 calls on a day, what is the chance that 4 of them were from strangers?
d)What is the probability that on a given day, he receives 2 calls from strangers and 3 calls from
acquaintances?
e) What is the probability that on a given day all calls he receives are from strangers?
8
44. If X has p.d.f. f (x) = 4x3, 0 < x < 1 then
a) Find the c.d.f. of X.
b) Compute the median of X.
c) Find the c.d.f. of Y = X2.
d) Find the p.d.f. of Y.
e) Compute the 90th percentile of Y.
45. Trains headed to a destination A arrive at station at 15-minute intervals starting at 7:10 A.M.,
whereas trains headed to destination B arrive at 15-minute intervals starting at 7 A.M. If a certain
passenger arrives at the station at a time that is uniformly distributed between 7 and 8 A.M, and
then gets on the first train that arrives what is the probability that the passenger travels to A?
46. You arrive at a bus stop at 10 A.M, knowing that the waiting time for the buses have an
exponential distribution with a mean of 30 minutes.
a) What is the probability that you will wait more than 10 minutes?
b) If at 10:15 am the bus has still not arrived, what is the probability that you will wait for at least
10 more minutes?
c) What is the probability of exactly two buses arriving during 10am-11am?
47. An average CFL is supposed to last for 1 year. Assume the lifetime is distributed exponentially.
Find the probability that
a) A CFL bulb last for 2 years or more.
b) Among the 5 CFL bulbs I have in my house, at least 4 last for 2 years or more.
c) On average, the 5 CFL bulbs in my house last for 2 years or more.
48. The annual net margins of a hundred year old company are known to be approximately normally
distributed. It has been observed that in 20 of the 100 years the net margins have fallen below 0 and
in 10 of the 100 years the margins have exceeded 5 crores. What can we say about the expected value
and the standard deviation of net margins?
49. A manufacturer makes shafts for electric motors. The external diameter is normally distributed
with mean 1 inch and SD 0.001 inch. The manufacturer purchases bushings which the shaft passes
through. The internal diameter of the hole in the bushing is normally distributed with mean 1.002
inch and sd 0.001 inch. When the shaft is put in the bushing the clearance is defined as the diameter
of the hole in the bushing minus the diameter of the shaft. Negative clearance means the shaft does
not fit.
a) For a shaft and bushing selected at random, what is the probability that the shaft does not fit?
b) To operate properly the clearance should be between 0.0016 and 0.0048 inch. What fraction of the
assembled units will be in this range?
50. A food processor packages instant coffee in small jars. The weights of the jars are normally
distributed with a standard deviation of 3 grams. If 5% of the jars weigh more than 124.92 grams,
then what is the mean weight of the jars?
9
51. A project has four phases viz. 1,2,3,4. A phase cannot start until the previous phase is completed.
The time to completion for each phase is believed to be normally distributed with means 6, 12, 4 and
8 weeks respectively and standard deviations 1,3,1 and 2 weeks respectively. Completion times of
the different stages are independent of each other.
a) What is the expected total time and SD of total time for completion of the project?
b) What is the probability that phase 3 can be started no later than 20 weeks from start?
c) If the project is scheduled to be completed in 32 weeks, what is the probability that it will be
completed in time?
d) What should be the planned duration if a probability of 80% is specified for in time completion of
the project?
52. There are three lunch specials in a restaurant: A, B and C, which cost Rs.100, Rs. 140 and Rs.
150 respectively. A student, who lunches in that restaurant every day, chooses these three specials
with probabilities 60%, 20% and 20% respectively. He chooses one lunch special every day
independently of his previous decisions.
a) Obtain the distribution of the student’s daily expenditure on lunch.
b) Obtain the distribution of the student’s average expenditure on lunch over two days.
c) Obtain the distribution of the student’s average expenditure on lunch over 50 days.
53. You manage a sales organisation consisting of 100 people. Each sales person is capable of selling
on an average 4 items per month. Based on your experience you have observed that the standard
deviation of sales made is 1.
a) What is the expected sales made by the organization in a month?
b) What is the probability that the total sales in the month exceeds 410 items? (State your
assumptions clearly.)
54. A volunteer tourist guide at a heritage site in India does not charge a fee for her services.
However, she accepts tips provided by the tourists. For every tourist she guides she receives either
a tip of 0 or 100 or 200 rupees with equal probabilities (i.e., = 1/3). Assume that this is her only source
of income. For questions a,b,c, assume that in a year she guides 5000 tourists.
a) What is her expected annual income?
b) What is the standard deviation of the annual income?
c) What is the probability that her income during the year will exceed Rs. 6,00,000?
d) Suppose that she wants to target an annual income of at least 600,000 in the sense that the
probability of her income falling below 600,000 should be less than 5%, then at least how many
tourists should she target to guide during the year?
55. According to a job website, every month around 20,000 people register in their website, and about
60% of them get placed within two weeks. Assuming that each person gets placed independently
with probability 0.6 within two weeks, what is the probability that at least 13,000 people get placed
within two weeks? What about 15,000?
10
Decision Making Under Uncertainty
2019–20 Session
i
C ONTENTS
Contents iii
1 Comparing Decisions Under Uncertainty and Risk 1

1.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Decision Making Under Deep Uncertainty . . . . . . . . . . . . . 3
1.3 Decision Making Under Risk . . . . . . . . . . . . . . . . . . . . . 4
1.4 Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2 Multistage Decision Making Under Risk 11

2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2.2 Representing multi-stage decision problems . . . . . . . . . . . 13
2.3 Solving multi-stage decision problems . . . . . . . . . . . . . . . 16
2.4 Sensitivity analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
2.5 Value of information . . . . . . . . . . . . . . . . . . . . . . . . . . 19
2.6 Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
iii
1
CHAPTER
C OMPARING D ECISIONS U NDER
U NCERTAINTY AND R ISK
1.1 Introduction
In this chapter we try to compare different decisions when the outcomes of
the decisions are not completely under the decision maker’s control. In partic-
ular, we consider situations in which the environment of the decision maker
is indifferent to the decision taken by the decision maker. So, the material that
we consider in this chapter does not naturally hold when the decision maker’s
decision is being scrutinised by a competitor, who will take a decision which
will maximise the competitor’s benefit, possibly to the detriment of the origi-
nal decision maker.
Consider for example, an investor who is trying to decide on an optimal in-
vestment portfolio. She has three different investment choices at his disposal,
which are i) debt funds (risk-free), ii)a mix of debt and equity funds (medium
risk), and iii) equity funds (high risk). She feels that there can be three broad
scenarios, i) improving economy, ii) stable economy and iii) worsening econ-
omy.
So the investor has three decision alternatives to choose from. Once she
decides on the investment option that she aims for, she will invest her money
in that for five years, and obtain a certain percentage of profit (or loss) at the
end of the time period. Table 1.1 shows the contributions to profits for differ-
ent investment choices under different scenarios. Such a table in which the
1
2 CHAPTER 1. COMPARING DECISIONS
What is a payoff payoffs for each strategy-scenario pair are listed is called a payoff table.
table?
Table 1.1: Payoff under different scenarios
Economic Condition (Scenario)

Investment Strategy Improving Stable Worsening
(Decision)
Debt 100 50 60
Mixed 150 60 0
Equity 180 10 -100
To decide on an optimal strategy of investment, the investor needs to con-

sider the payoff options. Notice from the payoff table that each decision al-
ternative is evaluated in terms of not one but three payoffs, corresponding to
the three scenarios that may arise. So comparing two strategies is not in terms
of comparing two numbers, but in terms of comparing two vectors of num-
bers. This is not easy; for example, investing in equity funds is better off than
investing in debt funds when economy is improving, but is worse off in the
other two scenarios. So the task of comparing strategies is the task of com-
bining the entries of the vectors of numbers corresponding to the strategies
into single numbers which can then be compared. While doing this, an idea
about the relative likelihood of the different scenarios is helpful. However,
such an idea may or may not be available. In this context, it is useful to realise
Levels of uncer- that uncertain decision making situations arise in a spectrum. On one end
tainty. of the spectrum are those situations in which decision scenarios either occur
completely at random, or due to processes which have so many contributing
factors that it is not realistic to assume that we will have enough information
to ascertain the likelihood of different scenarios. Such decision making sit-
uations are called situations of (deep) uncertainty. Such situations arise for
example, when one wants to predict the weather, say seven days in advance.
On the other end of the spectrum, there are situations in which the random
process giving rise to the scenarios are understood perfectly, and simple prob-
abilistic methods are useful to determine the likelihood of scenarios. Such
situations occur, for example, when one is betting on the throw of fair dice.
These situations are called situations of stochastic uncertainty or risk. Most
business scenarios fall somewhere in between; some but not all the important
determinants of a phenomenon are known, and collecting enough data about
the determinants will allow the decision maker to have a rough idea about the
likelihood of particular scenarios. These are situations in which management
tools such as market research become useful. In any scientific endeavor, the
idea is to start from the deep uncertainty end of the spectrum and move the
1.2. DECISION MAKING UNDER DEEP UNCERTAINTY 3
situation to the risk end of the spectrum through a better understanding of

the scenario and/or data collection.
The techniques used to make decisions about situations in different parts
of the spectrum are different, and are in general a mixture of techniques used
for deep uncertainty and risk. In the remainder of the chapter we explain
some of the techniques used for situations in the two ends of the spectrum.
1.2 Decision Making Under Deep Uncertainty

As mentioned earlier, when a decision maker makes decisions under uncer-
tainty, they do not know the probabilities with which each of the scenarios
occur. Hence they cannot have recourse to probabilities while making deci-
sions. There are two main techniques for making decisions under uncertainty,
which unfortunately make rather extreme risk profile assumptions.
The maximax approach

In this approach, the decision maker evaluates a decision strategy by the high-
est payoff that it can yield and ignores payoff values from all other scenarios.
For instance, in the example above, a decision maker following a maximax
approach will assign a payoff of 100 to investment in debt funds, although in
the other scenarios the payoffs from this strategy are lower. Hence a decision
maker who follows a maximax strategy is an extreme optimist. In our ongoing
example, the payoffs that the decision maker assigns to each of the strategies
is given in Table 1.2.
Table 1.2: Payoffs according to a maximax (or optimistic) approach

Investment Strategy Improving Stable Worsening Maximum
(Decision)
Debt 100 50 60 100
Mixed 150 60 0 150
Equity 180 10 -100 180
The decision maker then proceeds to choose that strategy for which the
payoff that they have assigned is the highest. In this example, they will be
choosing the equity funds.
Over time, decision makers who choose to follow the maximax strategy
can make large payoffs if observed scenarios are favourable in the long run.
However, if they are not, then such decision makers are liable to lose large
payoffs, and unless they have enough money in reserve, can be wiped out of
the market.
The maximin approach

This approach is diametrically opposite to the previous approach. If a deci-
sion maker follows this approach, then they evaluate a decision strategy by
the minimum payoff that it can yield, ignoring the other payoff values from
the strategy in other scenarios. In the example above for instance, such a deci-
sion maker will assign a payoff of 50 (%) to investment in debt funds, although
in the other scenarios the payoffs from this strategy are higher. Hence a de-
cision maker adopting a maximin decision making approach is an extreme
pessimist. In the example, the payoffs that the decision maker assigns to each
decision strategy is given in Table 1.3. The decision maker then proceeds to
Table 1.3: Payoffs according to a maximin (or pessimistic) approach

Investment Strategy Improving Stable Worsening Minimum
(Decision)
Debt 100 50 60 50
Mixed 150 60 0 0
Equity 180 10 -100 -100
choose that strategy for which the payoff that they have assigned is the high-
est. In this example, they will be choosing the debt funds.
Over time, decision makers who choose to follow the maximin strategy will
make small payoffs in each period. They will tend to avoid any strategy that
yields a negative payoff in the worst case.
1.3 Decision Making Under Risk

The two decision strategies described above suffer from the drawback that
they deal with decision makers who are either extremely risk prone or ex-
tremely risk averse. Decision makers do not typically show such extreme be-
havior. The approach that we discuss now addresses this drawback, provided
the decision maker has some idea about the chances of the scenarios that they
may face.
1.3. DECISION MAKING UNDER RISK 5
When a decision maker is taking decisions under risk (as opposed to un-
certainty) they have a fair idea about the chances of each of the scenarios
being realised. In other words, they know the probabilities of occurrence of
various scenarios. Under this condition, it is easier to combine the vector of
payoffs under different scenarios that each decision strategy entails into a sin-
gle number which can represent the effectiveness of a decision strategy.
Expected value approach

Consider a decision strategy for a decision maker which gives rise to a series
of payoffs corresponding to different scenarios that can unfold. If the deci-
sion maker knows the probability of the different scenarios, then the decision
maker can obtain a weighted sum of the payoffs from different scenarios in
which each payoff is weighted by the probability of the corresponding sce-
nario. This weighted sum is called the expected value of the distribution of
payoffs. For example, if the three scenarios of improving, stable and worsen-
ing economies occurred with probabilities 0.3, 0.5, and 0.2 respectively, then
the expected payoff associated with debt funds is
0.3 × 100 + 0.5 × 50 + 0.2 × 60 = 67.
Similar calculations show that the expected payoffs of the other two strategies,
mixed and equity, are respectively 75 and 39. The decision maker chooses the
scenario that maximises expected payoff, i.e., chooses the mixed investment
strategy whose expected payoff is 75.
When taking decision under risk, the most common strategy used is that
of maximising expected payoffs (or minimising expected costs for cost min-
imisation problems). A part of the reason for doing so is that expected values
is one of the best known measures for handling uncertain situations, and is
thus well-understood by all parties involved in decision making.
It may further be noted that the probabilities we assume for different sce-
narios here could be considered, in the language of classical probability set-
up, as prior probabilities. For that reason, sometimes this decision making
process based on the expected values computed using the prior probabilities
is referred to as Bayes’ decision rule, or Bayesian pre-posterior analysis.
Maximum Likelihood approach

In a setup when the probabilities of different scenarios is known, sometimes a
decision maker would simply restrict her attention to the situation most likely,
i.e., the situation with the highest probabilities, and then choose the decision
to maximise her profit in that situation. Such a strategy is known as maxi-

mum likelihood strategy. For example, for the ongoing example, one would
simply restrict their attention to the situation of stable economy, and choose
the dominant strategy(/strategies) for that situation, i.e., go for mixed invest-
ment.
While this approach is easy to understand, it is advisable to use the maxi-
mum likelihood approach when one scenario clearly dominates the other sce-
narios in terms of probability. For example, in a situation when one has ten
alternative scenarios with the highest probability of all being, say, 12%, then
obviously this approach is not a very sensible one, but when one scenario has
probability of realisation around, say, 70%, then using such an approach may
make sense.
However, we typically prefer the expected value approach to maximum
likelihood approach, except in very few very specific situations.
1.4 Problems
Problem 1.1: A wholesale shop sells crates of fresh (unprocessed) milk. Each
crate consists of 20 bottles. The shop procures crates at Rs.100 per crate, and
sells it at Rs.180 per crate. From past experience, the shop assesses the prob-
abilities of the daily demand for milk as follows:
Demand
(crates) Probability
1 0.1
2 0.1
3 0.3
4 0.3
5 0.2
Unprocessed milk is perishable, and milk procured on one day is considered

to be spoilt the next day. Spoilt milk has no value.
a. Draw the payoff table for the shop.
b. If the shop uses the maximax criterion to make decisions, how many crates
of milk should they stock each day? How many crates should they stock if
they use the maximin criterion?
c. What is the decision to the taken using the maximum likelihood criterion?
1.4. PROBLEMS 7
d. If the shop uses the expected value criterion to make decisions, how many
crates of milk should they stock each day? What would be the expected
profit for the decision that the shop takes?
Problem 1.2: The SciTool Company specialises in scientific instruments, and

has been invited to make a bid on a government contract. The contract calls
for a certain number of these instruments to be delivered during the coming
year. The bids must be sealed, so that no company knows what the others
are bidding. SciTool estimates that it will cost Rs.5000 to prepare a bid, and
Rs.95000 to supply the instruments if it wins the contract. Therefore, it has to
decide whether to submit a bid at all, and if it decides to submit a bid, then
whether to submit a bid for Rs.115000, or Rs.120000, or Rs.125000. On the ba-
sis of past contracts of this type, SciTool believe that there is a 30% chance that
there will be no competing bids. In case there are competing bids, then it esti-
mates that the probabilities of the lowest bid being less than Rs.115000 is 0.2,
between Rs.115000 and Rs.120000 is 0.4, between Rs.120000 and Rs.125000 is
0.3, and above Rs.125000 is 0.1. It also estimates that the chance of another
bid being exactly Rs.115000, or Rs.120000, or Rs.125000 is negligible.
a. Write down the entries in the payoff table for SciTool.
b. If SciTool uses the maximin approach to make a decision, what decision

should it take?
c. If SciTool wants to use the maximum likelihood approach, what decision

should it take?
d. How much payoff should SciTool expect if they decide to submit a bid for
Rs.120000?
e. If SciTool wants to maximise the expected payoff associated with their de-
cision, what decision should it take? What will be the value of the expected
payoff for their decision?
Problem 1.3: The Morton Company is considering the introduction of a new

product that is believed to have a p = 70% chance of being successful (and a
30% chance of being unsuccessful). If the product is ultimately successful, the
net profit to the company will be $15 million; if unsuccessful, the net loss will
be $25 million.
a. Assuming that the company follows a maximax decision criterion, what

decision should it take?
b. Assuming that the company follows a decision criterion of maximising ex-

pected net profits, what decision should it take?
c. Assume that the company follows a decision criterion of maximising ex-

pected net profits. Within what range of p values would the company’s
decision as computed in part (c) remain unchanged?
d. Assume that the company follows a decision criterion of maximising ex-

pected net profits. Within what range can the value of net profits from a
successful introduction vary before the company’s decision as computed
in part (c) changes? Assume for this question, that the net loss if the prod-
uct is unsuccessful remains the same.
Problem 1.4: A manufacturer must produce and deliver 1000 batches of a

particular chemical to a customer. The contribution to profits from each batch
is Rs.30. The manufacturing process of a certain chemical is not perfectly un-
der control. There is a 80% chance that 100 of the 1000 batches are substan-
dard, and a 20% chance that 300 of the 1000 batches are substandard. If the
manufacturer sends a substandard batch to the customer then the customer
demands a replacement for the substandard batch. The cost of replacing a
substandard batch with a perfect batch is Rs.400. The manufacturer has three
options for corrective action available to him.
Option 1: He can distill all the batches of the chemical at a cost of Rs.100 per
batch, and thus have no substandard batches sent to the customer.
Option 2: He can use a chemical reagent to test the quality of each batch at
a cost of Rs.20 per batch, and distill only those batches that are classi-
fied by the test as substandard at the cost of Rs.100 per batch. However
this test is inaccurate. While “good” batches never get classified as sub-
standard by the test, 5% of substandard batches get classified as “good”
and are not distilled. These batches when sent to a customer have to be
replaced at a cost of Rs.400 per batch replaced.
Option 3: He can use a specific gravity test which costs Rs.10 per batch, and
distill only those batches that are classified by the test as substandard at
the cost of Rs.100 per batch. This test is also not accurate. 10% of the
substandard batches get classified as “good” and have to be replaced
1.4. PROBLEMS 9
later (at a cost of Rs.400 per batch). The test also classifies 10% of the
good batches as “substandard”.
a. Draw the payoff table for the manufacturer.
b. If the manufacturer made decisions using the expected value criterion,

which of the options should he choose? What is the expected contribu-
tion to profits for this decision?
Problem 1.5: Tara owns a company that manufactures a fruit product called
CrunchyBites. A packet of this product contains 400gms of dry fruits and
100gms of sugar syrup, and is very popular among young children. It sells
for Rs.11 per packet in the market.
It is the end of the month and Tara has to decide on her purchasing and
manufacturing strategy for the next month. Her supplier for dry fruits is not
reliable; there is a 60% chance that he will supply 4000kg of dry fruits for a
month and a 40% chance that he will supply 6000kg. He supplies dry fruits at
Rs.10 per kilo. As per contract, Tara has to buy the full quantity of dry fruits
that the supplier supplies. She can buy any quantity of dry fruits from the
open market as she likes, but at Rs.15 per kilo.
Tara’s syrup supplier can supply any quantity of syrup that she wants. If
she orders syrup now, before the dry fruits supplier has supplied the dry fruits,
the syrup supplier charges Rs.5 per kilo of syrup. However, if she delays her
order till after her dry fruit supplier supplies dry fruits, the charge goes up to
Rs.7 per kilo of syrup.
Tara’s packing and related overheads come to Rs.2 per pack. She can man-
ufacture a maximum of 15000 packets of CrunchyBites in a month.
The monthly market demand for CrunchyBites is the following:
Demand 10000 packets 15000 packets

Chance 40% 60%
Unsold CrunchyBites packets are sent to a discount store to be sold at Rs.8

per packet. Excess dry fruits can also be sold at the same store at Rs.12 per
kilo. The discount store can sell as many CrunchyBites packets and as much
dry fruits as Tara sends them. Any excess syrup has to be thrown away.
Tara is considering the following four strategies:
Strategy 1: Buy 1500 kilos of syrup before the dry fruits supplier supplies fruits.
If the dry fruits supplier supplies 4000kg of fruits, then make and
sell 10000 packets of CrunchyBites; and if he supplies 6000kg, then

make and sell 15000 packets of CrunchyBites.
If the dry fruits supplier supplies 4000kg of fruits, then make and
sell 10000 packets of CrunchyBites; and if he supplies 6000kg, then
make and sell 15000 packets of CrunchyBites buying 500 kilos of
syrup at the higher price.
Make and sell 15000 packets of CrunchyBites, buying 2000kg of
dry fruits from the open market in case the dry fruits supplier sup-
plies 4000kg of fruits.
Regardless of the amount of fruits that the dry fruits supplier sup-
plies, make and sell 10000 packets of CrunchyBites.
a. What is the payoff from each of the strategies if the dry fruits supplier
supplies 4000kgs of dry fruits and the market demand for CrunchyBites
is 15000 packets?
b. What is the expected payoff from each of Tara’s strategies?
c. If Tara’s objective is to maximise her expected payoff, which of the four

strategies should she adopt?
d. What is the minimum chance of the demand being 15000 packets for which
your answer for part (c) remains unchanged?
e. Tara decides to insist that her dry fruit supplier supply her with 6000 kilos
of dry fruits every month. For this, the dry fruit supplier can increase his
price of dry fruits. What would be the maximum rate (Rs. per kilo of dry
fruits) that she should be prepared to pay?
2
CHAPTER
M ULTISTAGE D ECISION M AKING
U NDER R ISK
2.1 Introduction
Consider the example provided in Section 1.1. In the example, the decision
maker has to make her decision in one time point; the product mix that she
needs to aim for, and whether to produce tables first, or whether to produce
chairs first. In the majority of decision making scenarios, the decision mak-
ing is more complex. It involves making multiple decisions at different points
in time, and decisions made earlier have an effect on the payoffs of decisions
made later. In this chapter we study such multi-stage decision making situa-
tions.
We make two assumptions in this chapter. The first is that these situations Assumptions.
are of stochastic uncertainty, and each uncertain event is associated with a
probability of encountering it. The second assumption is that we evaluate dif-
ferent strategies of the decision maker in terms of the expected value criterion
described in Section 1.3. Although these assumptions are generally accepted
in practice, it is possible to consider situations in which they are not appro-
priate. The methods for dealing with such violations are not covered in this
chapter.
In order to understand multi-stage decision making processes, consider
the following decision problem faced by the production manager of a com-
pany X. The company produces a product which is seeing large increases in
11
12 CHAPTER 2. DECISION TREES
market demand. The company’s current production facility is not enough to

meet the demand for the product. In addition to the option of asking the pro-
duction staff to work overtime, the production manager has two more options
to consider. The first option is to subcontract the manufacturing of additional
units of the product to another company, Y. The manager feels that there is an
80% chance that Y will be able to fill the additional demand reliably. In that
case, X will make a profit of Rs.12 lakhs over what it is currently making over
the life-cycle of the product. If Y cannot fill the demand reliably (i.e., their per-
formance is erratic), then X loses Rs.4 lakhs due to various contractual obliga-
tions. The second option is for the production manager to approach the com-
pany’s board asking for permission to augment the production facility. The
manager feels that the chance of approval is 70%. If the board approves the
request, the manager expects an additional profit of Rs.14 lakhs over the life-
cycle of the product. If the board rejects the request, the production manager
can either continue with his current facility and pay overtime to his staff, or
subcontract the production to company Y. In case he goes for overtime pay-
ment, he expects to earn an additional profit of Rs.5 lakhs over the life-cycle
of the product. If he subcontracts production to Y at this stage, he expects
the additional profit to be Rs.10 lakhs if Y fills the product reliably, and the
expected loss to be Rs.5 lakhs if they do not. The decision making problem is
one of figuring out what the production manager should do.
A solution to a decision problem must specify a course of action in all sce-
narios, and so even though the immediate decision that the production man-
ager needs to take is to choose between going for overtime, or for subcontract-
ing, or for approaching the board with a proposal for capacity augmentation,
solution alternatives for the manager are the following.
Strategy A: Proceed with same capacity and overtime payment.
Strategy B: Subcontract to company Y.
Strategy C: Approach the board with a proposal to augment capacity, and if

they reject the proposal go for paying overtime.
Strategy D: Approach the board with a proposal to augment capacity, and if

they reject the proposal, subcontract to company Y.
At the end of the life-cycle of the product, the production manager will
find himself in one of the following scenarios.
Scenario I: No proposal was made, and the production staff worked over-
time. (Additional profit was Rs.5 lakhs.)
2.2. REPRESENTING MULTI-STAGE DECISION PROBLEMS 13
Scenario II: No proposal was made, company Y’s service was used, and com-
pany Y delivered reliably. (Additional profit was Rs.12 lakhs.)
Scenario III: No proposal was made, company Y’s service was used, and com-
pany Y delivered erratically. (Loss of profit was Rs.4 lakhs.)
Scenario IV: A proposal was made and accepted, so that the production fa-
cility was augmented. (Additional profit was Rs.14 lakhs.)
Scenario V: A proposal was made and rejected, and the production staff work-
ed overtime. (Additional profit was Rs.5 lakhs.)
Scenario VI: A proposal was made and rejected, company Y’s service was used,
and company Y delivered reliably. (Additional profit was Rs.10 lakhs.)
Scenario VII: A proposal was made and rejected, company Y’s service was
used, and company Y delivered erratically. (Loss of profit was Rs.5 lakhs.)
Note that every decision scenario will not be observed for each of the de-
cision strategies. For example, if the production manager decides to adopt
strategy B, he will only see one of Scenarios B and C. If we construct a payoff
table for this problem, the table will be
Scenario
Strategy I II III IV V VI VII
A 5
B 12 −4
C 14 5
D 14 10 −5
In addition, the probability of occurrence of each of the scenarios will be dif-

ferent for each of the decision strategies.
Hence there is a need for a more elegant way of representing and solving
multi-stage decision problems. We will see that method in the next section.
2.2 Representing multi-stage decision problems

Since the payoff table is a cumbersome way of representing multi-stage prob-
lems, one uses a more elegant “graphical” method to represent such prob-
lems. The representation is over time; the left hand side of the diagram rep-
resenting the present while the right hand side representing the future. Each
sequence of decisions and events that make up the realisation of the effects of
a decision strategy is represented as a path in the diagram from the present to
the future.
A diagram that shows all possible realisations in a decision problem is one
which starts at a single point on the left corresponding to the present situation
(before the decision making process starts) and then fans out to the right, with
paths representing different possible realisations. For the decision problem
that we consider, this diagram is shown in Figure 2.1. Each scenario represents
Pay
overtime Payoff:
Rs.5 lakhs
Company Y is
reliable Payoff:
Rs.12 lakhs
a b
Approach
Company Y
Payoff:
Company Y is – Rs.4 lakhs
erratic
Proposal is
approved Payoff:
Rs.14 lakhs
Pay
overtime Payoff:
c
Send proposal Rs.5 lakhs
to the board
Company Y is
d reliable Payoff:
Proposal is
rejected Rs.10 lakhs
e
Approach
Company Y
Payoff:
erratic
Figure 2.1: A diagram showing all realisations for the problem
a state at the end of the problem reached by a path (i.e., a realisation) from the
left to the right. The payoff to be achieved in the scenario is also marked in the
diagram.
At every junction in the tree (represented by letters from ‘a’ through ‘e’)
there is a possibility of choosing one of multiple realisations. There is how-
ever a difference in the way paths are followed at each junction. In junctions
‘a’ and ‘d’ it is up to the decision maker, the production manager in this case,
2.2. REPRESENTING MULTI-STAGE DECISION PROBLEMS 15
to choose which of the paths he wishes to take. In the other three junctions,
the choice of paths is through a random process, and the decision maker can-
not guide the choice. In the problem situations that we consider, the choice
of paths happen with pre-specified probabilities. If we add these bits of infor-
mation, i.e., the distinction between junctions where the decision maker can
choose paths and where he cannot, and the probabilities with which paths
are chosen at junctions where the decision maker cannot choose the paths,
we obtain an enhanced version of the diagram in Figure 2.1 called a decision
tree. By convention, we represent junctions in which the decision maker can What is a deci-
choose paths with squares and call them decision nodes, while the other junc- sion tree?
tions are represented by circles and are called chance nodes or event nodes.
The probabilities of paths being chosen at each chance node is also added to
the diagram to form the decision tree. Figure 2.2 shows the decision tree for
the production manager’s problem.
Pay
overtime Payoff:
Rs.5 lakhs
Company Y is
reliable Payoff:
p = 0.8 Rs.12 lakhs
a b
Approach
Company Y
p = 0.2 Payoff:
erratic
Proposal is
approved Payoff:
p = 0.7 Rs.14 lakhs
Pay
overtime Payoff:
c
Send proposal Rs.5 lakhs
to the board
p = 0.3 Company Y is
d reliable Payoff:
Proposal is
rejected p = 0.8 Rs.10 lakhs
e
Approach
Company Y
p = 0.2 Payoff:
erratic
Figure 2.2: The decision tree for the problem
Note that a decision tree is merely a graphical representation of a multi-

stage decision problem with all data for the problem represented conveniently.
In the next section we will see how to analyze decision trees and choose an op-
timal decision strategy.
2.3 Solving multi-stage decision problems

Given the decision tree representation of the production manager’s problem,
we now solve the problem and arrive at the optimal decision for the manager.
Recall that by our assumption, the production manager uses the expected
value criterion for comparing decision alternatives and choose a decision that
maximises the expected payoff.
Any decision strategy for this problem answers at least one of two ques-
tions; (1) the immediate question of whether to pay overtime, subcontract, or
make a proposal to the board (as depicted by decision node ‘a’ in the decision
tree of Figure 2.2, and (2) the question of what to do if a proposal is made and
rejected by the board (as depicted by decision node ‘d’. Of course for some de-
cision strategies (such as strategy A and strategy B) the second question does
not arise, but since we do not know beforehand whether one among strate-
gies A and B would be optimal, we need to answer both the questions. In
other words, a solution to a decision tree prescribes an optimal choice at each
decision node, whether it is reached or not.
Now consider the optimal choice at decision node ‘a’. Since the produc-
tion manager is an expected value maximiser, the choice that he will make at
node ‘a’ is the one among the three alternatives that will earn him the maxi-
mum expected payoff. However, we do not know the expected payoff in two of
the three choices (they lead to chance nodes ‘b’ and ‘c’), and so to arrive at this
decision, we need to compute the expected payoffs at ‘b’ and ‘c’. It is obvious
therefore that our analysis of the decision tree should start at the right hand
side of the tree and roll back towards the left, making appropriate decisions
whenever possible. Consider node ‘e’ for example. This is a chance node, and
hence the expected payoff at ‘e’ is Rs.(10 × 0.8 − 5 × 0.2) lakhs i.e., Rs.7 lakhs.
Similarly, the expected payoff at chance node ‘b’ is Rs.(12 × 0.8 − 4 × 0.2) lakhs
or Rs.8.8 lakhs. Once we calculate the expected payoff at ‘e’, we are in a posi-
tion to determine the decision at node ‘d’. At node ‘d’ the choice is between
paying overtime and earning a payoff of Rs.5 lakhs and of approaching com-
pany Y and earning an expected payoff of Rs.7 lakhs. For an expected payoff
maximiser, the choice of course is the latter, and hence if the production man-
ager makes a proposal to the board and the board rejects it, it is optimal for
the production manager to approach company Y. Having made this decision,
we know that should the decision maker reach node ‘d’ then his expected pay-
2.4. SENSITIVITY ANALYSIS 17
off is Rs.7 lakhs (the maximum of Rs.5 lakhs and Rs.7 lakhs). This allows us to
compute the expected payoff at chance node ‘c’ as Rs.(14 × 0.7 + 7 × 0.3) lakhs
or Rs.11.9 lakhs. Having computed the expected payoff at node ‘c’, we can
combine this information with the expected payoff at node ‘b’ and the given
payoff at the other node to ascertain that at node ‘a’, the optimal strategy is
to send the proposal of capacity augmentation to the board. And combining
the optimal decisions at decision nodes ‘a’ and ‘c’, we come to the conclusion
that the optimal strategy for the production manager is strategy C, i.e., to send
in a proposal for capacity augmentation to the board, and in case the board
rejects the proposal, to approach company Y with a subcontracting offer. The
expected payoff for this strategy is Rs.11.9 lakhs.
At this point we should be clear about out interpretation of the expected
payoff value of Rs.11.9 lakhs. This figure is an expected value. So this means
that if the production manager faced the same decision problem a large num-
ber (tending to an infinite number) of times, applied strategy C every time,
and computed the average of all the payoffs he received, the average payoff
would be Rs.111.9 lakhs. Every time he takes the decision, he stands to earn
Rs.14 lakhs with probability 0.7, Rs.10 lakhs with probability 0.3 × 0.8 = 0.24,
and lose Rs.5 lakhs with probability 0.3 × 0.2 = 0.06.
2.4 Sensitivity analysis

While computing an optimal decision strategy for the production manager,
we have chosen a 0.7 probability value for a proposal made to the board be-
ing accepted, and a 0.8 probability value of company Y delivering the product
reliably. In any practical scenario, it is almost certain that these probabilities
do not have these exact values, although we expect them to be close to the
chosen values. An important part of analyzing decision trees is to find out
how robust the optimal decision is to changes in these parameters, or in other
words, for what ranges of these probability values does the optimal decision
strategy remain optimal. Notice that we do not make any claim about the ex-
pected payoff from the optimal strategy, but merely ask for the strategy not to
be worse than any other strategy in expected value terms. Such an analysis,
when we allow the value of exactly one of the parameters to change, is called
sensitivity analysis. In the remainder of this section, we demonstrate how to
perform sensitivity analysis on decision trees.
Consider any probability value associated with the production manager’s
decision problem. This could either be the probability that a proposal of ca-
pacity expansion made to the board is accepted, or the probability that com-
pany Y delivers reliably. Let us denote the chosen probability value by p. Now,
since there are two decision nodes ‘a’ and ‘d’ in the decision tree in Figure 2.2,
any change in the optimal strategy will be reflected as a change in the opti-
mal decision at one or both of these decision nodes. Now let us suppose that
submitting a proposal of capacity
£ a expansion to the board remains the opti-
a
¤
mal decision at node ‘a’ if p ∈ p l , p h , and approaching company Y remains
the optimal decision at node ‘d’ if p ∈ p ld , p hd . Then the range of p for which
£ ¤
strategy C remains optimal is
range = max p la , p ld , min p ha , p hd .

£ © ª © ª¤
Consider the probability value p = 0.7 for a proposal on capacity expan-

sion made to the board being accepted. When we find the allowable range of
p, we consider the other probability (that of company Y delivering reliably)
to remain unchanged. In that case, there is no change in the expected payoff
at node ‘e’ and the decision at node ‘d’ remains unchanged whatever be the
value of p. Hence we can conclude that the optimal decision at node ‘d’ for
Strategy C remains unchanged if p ∈ [0, 1]. The expected payoff at node ‘b’ is
not affected by changes in p and remains unchanged at Rs.8.8 lakhs. The ex-
pected payoff at node ‘c’, calculated as Rs.14p +7(1− p) lakhs = Rs.7p +7 lakhs
obviously changes with the value of p. The decision at node ‘a’ will remain
unchanged when this payoff does not fall below max{Rs.5 lakhs, Rs.8.8 lakhs}
= Rs.8.8 lakhs. So the decision remains unchanged when 7p + 7 ≥ 8.8 or p ≥
0.257. Therefore the optimal decision at node ‘a’ for Strategy C remains un-
changed if p ∈ [0.257, 1]. Combining these values we see that Strategy C re-
mains unchanged when the probability for a proposal made to the board be-
ing accepted is in the range [0.257,1].
Next consider the probability value r = 0.8 of company Y delivering reli-
ably. Similar to the earlier case, when we consider changes in this value, we
assume that the probability that the board accepts a proposal for capacity ex-
pansion remains fixed at 0.7. When the value of r changes, the expected pay-
offs at nodes ‘b’ and ‘e’ obviously change. In terms of r , the expected payoff
at node ‘b’ is Rs.12r − 4(1 − r ) lakhs = Rs.16r − 4 lakhs and that at node ‘e’ is
Rs.15r − 5 lakhs. In the optimal strategy before the change, i.e., in Strategy C,
the decision at node ‘d’ is to approach company Y. So as the value of r changes,
the expected payoff at node ‘d’ also changes to Rs.15r − 5 lakhs. The expected
payoff at node ‘c’ changes since the expected payoff at node ‘d’ changes, and
becomes Rs.11.2+0.3(15r −5) lakhs = Rs.4.5r +9.7 lakhs. The optimal decision
at at node ‘d’ before the value of r changes remains optimal as long as the ex-
pected payoff at node ‘e’ does not fall below Rs.5 lakhs, i.e., 15r − 5 ≥ 5, i.e.,
r ∈ [0.667, 1]. Similarly, the optimal decision at node ‘a’ before the value of r
changes remains optimal as long as 4.5r + 9.7 ≥ max{5, 16r − 4}. As this always
2.5. VALUE OF INFORMATION 19
happens, the optimal decision at node ‘a’ remains optimal when r ∈ [0, 1].
Therefore, strategy C remains unchanged when the probability of company
Y acting reliably is in the range [0.667,1].
It is important to reiterate a few points at this stage. First, when perform-
ing sensitivity analysis, the objective is to find the range of probability values
for which a complete decision strategy remains optimal. Hence it is not suf-
ficient to account only for changes at any one decision node. Note that the
decision at a decision node can change only when the payoffs for at least one
of the alternatives at that node changes. So if a probability value changes, then
decisions “downstream” to the position where that probability value occurs in
the decision tree do not change. Also, any decision “upstream” to that posi-
tion can change only if there are no intermediate decision nodes that filter out
the effect of the change (by choosing a decision alternative which does not lie
on the same path.)
2.5 Value of information

Recall that the decision maker’s criterion for evaluating alternatives is one of
maximising expected payoffs, which means that implicitly they averaging re-
turns from a large number of identical situations. However, since the present
decision situation is not likely to be repeated identically several times, the de-
cision maker can benefit with any expert advice that pertains to the situation
at hand. For example, in the decision problem that we consider in this chap-
ter, the decision maker is more concerned about the board’s response to this
particular capacity expansion proposal rather than to the board’s response for
capacity expansion proposals in general. Also, he is more concerned about
the ability of company Y to deliver this particular product reliably rather than
that of company Y’s general ability to deliver products reliably. Therefore,
the decision maker (the production manager in our case) will assign a value
to expert advice about their current situation. In this section, we describe a
method to compute the worth of such advice. We first consider the utopian
case of an expert who is perfect, i.e., never makes mistakes, and then consider
more practical fallible experts. In both cases, we compute the worth of the ad-
vice as the increase in expected payoffs that the decision maker achieves with
the expert’s help.
Expected value of perfect information

Consider a perfect expert. In our example, suppose that this expert is infallible
at predicting whether or not company Y will deliver the product reliably. How
much is the advise of such an expert worth to the production manager?
Note that the advise of the expert is worth something to the production
manager before he takes the decision of whether or not to approach company
Y. After the decision has been taken the expert’s advice is of no practical use
since the production manager cannot take advantage of the advice to make
better decisions. Also note that since the expert is always right, and company
Y delivers reliably 80% of the time, the expert will say that company Y will de-
liver reliably with a probability of 0.8. However, in a given situation they will
respond with a definite YES or a definite NO, and not make probabilistic state-
This is an im- ments. Also note that since the expert is always right, the decision maker will
portant point to not second-guess the expert, and will take the expert’s decision as the truth
keep in mind. while taking decisions. (This point seems trivial in the present case, but will
be more consequential when we consider fallible experts.)
We know that without the expert’s advice, the optimal strategy for the pro-
duction manager is strategy C which yields an expected payoff of Rs.11.9 lakhs
(see Section 2.3). We also know that in case the expert says that company Y will
deliver reliably, the manager does not need to consider the option of paying
overtime, since the payoff from approaching company Y will be more than
that from paying overtime. Additionally we know that if the expert says that
company Y will not deliver reliably, then the manager does not need to con-
sider the option of approaching them, since the payoff from paying overtime
is higher. So when there is an option of asking the expert, the decision tree for
the decision process is the one shown in Figure 2.3.
Solving the decision tree we find that the expected payoff if the decision
maker decides to consult the expert is Rs.12.5 lakhs. In this diagram, the op-
timal strategy is to consult the expert (at decision node ’a’) and to approach
the board with a proposal no matter what the expert says (at decision nodes
‘c’ and ‘d’). If the board rejects the proposal, they should approach company Y
if the expert says that they will be reliable in their deliveries, and pay overtime
otherwise. The reason that the expert’s advice earns the production manager
a higher expected payoff is that the expert prevents the production manager
from ending up in scenarios in which he would lose money.
Since the expected payoff with access to the expert is Rs.12.5 lakhs while
that without access to the expert is Rs.11.9 lakhs, the worth of the expert’s
opinion is calculated to be Rs.12.5 lakhs - Rs.11.9 lakhs = Rs.0.6 lakhs. This
figure is an expected payoff figure obtained by assuming perfect information
What is EVPI? from the expert. So this figure is called the Expected Value of Perfect Informa-
tion (EVPI).
2.5. VALUE OF INFORMATION 21
Do not ask the

expert Expected Payoff:
Rs.11.9 lakhs
Approach
Company Y Payoff:
Rs.12 lakhs
a Expert says that
Y is reliable Proposal is
c approved Payoff:
p = 0.8 Rs.14 lakhs
p = 0.7
e
Approach board
with proposal
p = 0.3 Payoff:
Proposal is rejected Rs.10 lakhs
b (approach Y)
Ask the expert
Pay
overtime Payoff:
Rs.5 lakhs
p = 0.2 Proposal is
d approved Payoff:
Expert says that
Y is erratic p = 0.7 Rs.14 lakhs
f
Approach board
with proposal
p = 0.3 Payoff:
Proposal is rejected Rs.5 lakhs
(pay overtime)
Figure 2.3: The decision tree with access to perfect information
Expected value of sample information
Next consider an imperfect expert. The imperfection of the expert can lead
the decision maker to two types of mistakes. The first type of mistake is when
an expert states in error that company Y will deliver reliably when it actually
delivers erratically. In such situations, if the production manager follows the
expert, then he makes a monetary loss. The second type of mistake is when
the expert erroneously states that company Y will be erratic in their delivery
when they actually deliver reliably. In this situation, if the production man-
ager follows the expert’s advice, then he will prefer paying overtime to ap-
proaching company Y and will settle for a lower payoff, thus incurring op-
portunity losses. Both these errors clearly do not occur for a perfect expert,
simply because such experts are infallible. These errors are also the reason
why an imperfect expert’s advice cannot be worth more than that of a perfect
expert.
Why should one take advice from an imperfect expert when we know that
an imperfect expert makes mistakes and can advise a decision maker into sit-
uations in which the decision maker suffers monetary or opportunity losses?
One takes such advice because when the imperfect expert is correct in their
decision, they can prevent a decision maker from taking decisions that lead to
losses. One expects the latter type of situations to be more frequent than situ-
ations in which the expert makes mistakes, and in the expected value sense, a
decision maker is better off with an imperfect expert’s advice than without it.
It is also this reason that suggests that the decision maker follows the expert’s
advice even though there is a chance that the expert had made a mistake in
judgement. The decision tree with the option of asking an imperfect expert is
shown in Figure 2.4. Note that we have not determined the probability with
which such an expert will say that company Y will deliver reliably.
In order to compute the worth of an imperfect expert’s advice, we need to
find out the probability p with which the expert will say that company Y will
deliver reliably. Data on the expert’s past decisions can help us find the value
of p using Bayes’ rule. Consider for instance in our example, we have an expert
who when she says that company Y will deliver reliably is correct 90% of the
time, and when she says that they will deliver erratically is correct 80% of the
time. The joint probability of company Y delivering reliably and the expert
saying that they will is 0.9p and the joint probability of company Y delivering
reliably and the expert saying that they will not is (1 − 0.8)(1 − p). So in terms
of p, the probability that company Y will deliver reliably is 0.9p + 0.2(1 − p) =
0.7p +0.2. We know this value is actually 0.8, so that 0.7p −0.2 = 0.8 or p = 6/7.
This means that such an expert will say that company Y will deliver reliably
6/7-th of the time.
Solving the decision tree we find that the expected payoff if the decision
maker decides to consult the expert is Rs.12.2 lakhs. The optimal strategy for
the production manager in this situation is to ask the expert at node ‘a’ and
submit a proposal to the board at nodes ‘e’, ‘f’, ‘g’, and ‘h’. If the board rejects
the proposal, the production manager should approach company Y if the ex-
pert says that they are reliable, and pay overtime otherwise. In the diagram,
the expert’s erroneous advice causes the production manager to face a possi-
ble monetary loss at chance node ‘k’, and an opportunity loss at chance nodes
‘l’ and ‘m’.
Since the expected payoff with access to the imperfect expert is Rs.12.2
lakhs while that without access to the expert is Rs.11.9 lakhs, the worth of
the expert’s opinion is calculated to be Rs.12.2 lakhs - Rs.11.9 lakhs = Rs.0.3
What is EVSI? lakhs. As with EVPI, this figure is an expected payoff figure. In practice, since
imperfect information is most often obtained through sampling studies, this
expected value is called Expected Value of Sample Information (EVSI).
2.6. PROBLEMS 23
Expert is right
Payoff Rs. 12 Lakhs
Do not ask the Expected Payoff Probability
expert Rs. 11.9 Lakhs 0.9
Approach Y
d
Expert is wrong
Expert says Y is Payoff Rs. -4 Lakhs
reliable Probability 0.1
a Probability p c
Proposal is
approved
Payoff Rs. 14 Lakhs
Probability 0.7
Approach board
with proposal e
Expert is right
Payoff Rs. 10 Lakhs
Proposal is Probability
rejected, 0.9
b approach Y
Ask the expert f
Probability 0.3
Expert is wrong
Pay overtime Payoff Rs. -5 Lakhs
Payoff Rs. 5
Probability 0.1
Lakhs
Expert says Y is
Proposal is
erratic
g approved
Payoff Rs. 14 Lakhs
Probability 1-p
Probability 0.7
h
Approach board
with proposal Proposal is
rejected, pay
overtime
Payoff Rs. 5 Lakhs
Probability 0.3
Figure 2.4: The decision tree with access to imperfect information

2.6 Problems
Problem 2.1: A complex airborne navigating system incorporates a sub-ass-
embly which unrolls a map of the flight plan synchronously with the move-
ment of the aeroplane. This sub-assembly is bought on very good terms from
a subcontractor, but is not always in perfect adjustment on delivery. The sub-
assemblies can be readjusted on delivery to guarantee accuracy at a cost of
$220 per sub-assembly. It is not however, possible to distinguish visually those
assemblies that need adjustment.
Alternatively, the sub-assemblies can each be tested electronically to see
if they need adjustment at a cost of $48 per sub-assembly tested. Past experi-
ence shows that about 40 percent of those supplied are defective; the proba-
bility of the test indicating a bad adjustment when the sub-assembly is faulty
is 0.7, while the probability that the test indicates a good adjustment when the
sub-assembly is properly adjusted is 0.8. If the adjustment is not made and
the sub-assembly is found to be faulty when the system has its final check,
the cost of subsequent rectification will be $600.
Draw up a decision tree to show the alternatives open to the purchaser and
use it to determine his appropriate course of action.
Problem 2.2: A company prospecting for minerals divides its exploration area
into ten plots, intending to drill to a depth of 300 feet near the center of each
plot. Geological data suggest that the ten plots are either wholly within a large
mineral field discovered in a neighbouring area or wholly outside the field,
and that there is a 50:50 chance of either. Drilling to 300 feet within the field
would give a 50% chance of a strike, whereas outside the field there would be
virtually no chance of a strike.
On striking minerals the total operating profit can be expected to be $50
million, excluding the cost of exploratory drilling, the cost of which is $100,000
per hole.
After each hole has been drilled a decision is made whether or not to con-
tinue drilling with the next hole. The criterion used for this decision is whether
the expected drilling cost, not including the holes already drilled, exceeds the
expected operating profit.
1. What is the probability that the plots lie within the field, given that no
successful holes have been drilled in k attempts, 1 ≤ k ≤ 10?
2. How many unsuccessful holes will the company drill before abandoning
the search, and what is the expected drilling cost before the operation
starts?
2.6. PROBLEMS 25
Problem 2.3: There is 60% chance that there are oil-bearing rocks under a
piece of land. With current technology, if a region contains oil-bearing rocks,
there is 80% chance that if an oil and gas company drills a well in that region,
they will hit oil. It requires 1 million dollars to drill a well, and the revenue
earned from the oil extracted is 3 million dollars. The oil and gas company
wants to maximise profits, and follows the expected value criterion to decide
whether to drill a well in that piece of land.
a. Will the company drill a well in that piece of land? What is the expected
value of their best decision?
b. What is the expected value of perfect information in this case?
The company has the option of drilling zero, one, or two wells in that piece of
land. If they decide to drill wells, their decision to drill a second well depends
on the outcome of their drilling the first well.
c. Assume that the company drills a well and the well that they drill hits oil.
How does this fact revise the chance of the presence of oil-bearing rocks
under that piece of land? How does it affect the chance of the company
hitting oil under that piece of land?
d. Assume that the company drills a well and the well that they drill DOES
NOT hit oil. How does this fact revise the chance of the presence of oil-
bearing rocks under that piece of land? How does it affect the chance of
the company hitting oil under that piece of land?
e. Under this policy of deciding on drilling the second well depending on the
result of drilling the first well, what is their expected profit?
Problem 2.4: ABC Company is in the business of manufacturing widgets. The

market size of widgets is 1000 widgets. The market share of a company is as-
sessed by a probability distribution given below:
Market Share 10% 20% 40%

Probability 0.3 0.3 0.4
The company can make widgets by one of the two processes A and B. Pro-
cess A involves a fixed cost of Rs.10,000 and a variable cost of Rs.40 per widget
produced. Process B involves a fixed cost of Rs.16,000 and a variable cost of

Rs.20 per widget produced.
a. Which of the two processes is the better choice for the company if it wants
to minimise expected manufacturing cost?
b. Within what ranges of probabilities will the choice that you suggest in part
(a) remain the better choice? (You may need to solve this problem numer-
ically.)
Problem 2.5: The Alpha-Omega Company is unsure about its market share
for a particular product. The market share could be 10%, 15%, or 35%. The
company’s initial guess about the chances of the market share being these
values are 0.20, 0.35, and 0.45 respectively. The size of the market is 200. If the
company decides to manufacture the product using process A, then it incurs
a fixed cost of Rs.25,000 and a variable cost of Rs.1200 per unit. If it manufac-
tures the product using process B, then it incurs a fixed cost of Rs.50,000 and
a variable cost of Rs.400 per unit.
a. Write down costs of the two processes under different market share situa-
tions.
b. Which of these two processes should the company use under the expected
value criterion? What would be the expected value of cost incurred?
c. The company is quite sure about the 0.20 probability of their market share
being 10% but are unsure of the other two probability values. Within what
range of probability values for the market share being 15% would their de-
cision in Part (b) remain optimal?
Problem 2.6: Consider the ABC Company of Problem 2.4. The company de-
cides to hire the services of a market research firm to have a better idea of its
actual market share. The market research firm charges a flat fee of Rs.100 re-
gardless of the sample size and an additional charge of Rs.10 per respondent
sampled.
a. What is the expected value of perfect information for ABC Company?
b. What is the maximum number of respondents that ABC Company can ask
the market research firm to sample?
2.6. PROBLEMS 27
c. If the market research firm samples 5 respondents and 2 out of the 5 sam-
pled say that they would buy the widgets manufactured by ABC Company,
which of the two processes should ABC Company use to manufacture wid-
gets if they desire to minimise the expected cost of manufacturing wid-
gets? What is their expected manufacturing cost using this process?
d. What is the expected value of sample information for a sample size of 5

respondents?
Problem 2.7: Consider the Alpha-Omega Company in Problem 2.5. In order

to better ascertain its market share, the company decides to contact a mar-
ket research agency to ask customers of the product whether they use Alpha-
Omega’s product. The market research agency charges a fixed cost of Rs.200
and a variable cost of Rs.50 per customer contacted. Assume that Alpha-
Omega asks the agency to contact 18 customers.
a. What is the expected value of perfect information in this situation?
b. If 2 out of the 18 say that they use Alpha-Omega’s product, which of these
two processes should the company use?
c. If 3 out of the 18 say that they use Alpha-Omega’s product, which of these
two processes should the company use?
d. Compute the EVSI if the company asks the market research agency to con-
tact 18 customers. What is the expected value of the company’s net gain
from this sampling survey?

Course Material BM QT 2019 PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Course Material BM QT 2019 PDF

Uploaded by

Copyright:

Available Formats

XLRI, Jamshedpur PGDM (BM) 2019

Instructor: Apratim Guha

Suggested Additional Reading:

Sessions Topics Reading

a) What is the probability that he really has the disease?

26. Consider a random variable X with the following distribution:

a) P(X > 0),

a) Obtain the marginal distributions of X and Y.

1 Comparing Decisions Under Uncertainty and Risk 1

2 Multistage Decision Making Under Risk 11

Economic Condition (Scenario)

To decide on an optimal strategy of investment, the investor needs to con-

situation to the risk end of the spectrum through a better understanding of

1.2 Decision Making Under Deep Uncertainty

The maximax approach

Table 1.2: Payoffs according to a maximax (or optimistic) approach

Economic Condition (Scenario)

The maximin approach

Table 1.3: Payoffs according to a maximin (or pessimistic) approach

Economic Condition (Scenario)

1.3 Decision Making Under Risk

Expected value approach

0.3 × 100 + 0.5 × 50 + 0.2 × 60 = 67.

Maximum Likelihood approach

to maximise her profit in that situation. Such a strategy is known as maxi-

Unprocessed milk is perishable, and milk procured on one day is considered

a. Draw the payoff table for the shop.

Problem 1.2: The SciTool Company specialises in scientific instruments, and

a. Write down the entries in the payoff table for SciTool.

b. If SciTool uses the maximin approach to make a decision, what decision

c. If SciTool wants to use the maximum likelihood approach, what decision

Problem 1.3: The Morton Company is considering the introduction of a new

a. Assuming that the company follows a maximax decision criterion, what

b. Assuming that the company follows a decision criterion of maximising ex-

c. Assume that the company follows a decision criterion of maximising ex-

d. Assume that the company follows a decision criterion of maximising ex-

Problem 1.4: A manufacturer must produce and deliver 1000 batches of a

a. Draw the payoff table for the manufacturer.

b. If the manufacturer made decisions using the expected value criterion,

Demand 10000 packets 15000 packets

Unsold CrunchyBites packets are sent to a discount store to be sold at Rs.8

sell 10000 packets of CrunchyBites; and if he supplies 6000kg, then

b. What is the expected payoff from each of Tara’s strategies?

c. If Tara’s objective is to maximise her expected payoff, which of the four

market demand. The company’s current production facility is not enough to

Strategy A: Proceed with same capacity and overtime payment.

Strategy B: Subcontract to company Y.

Strategy C: Approach the board with a proposal to augment capacity, and if

Strategy D: Approach the board with a proposal to augment capacity, and if

In addition, the probability of occurrence of each of the scenarios will be dif-

2.2 Representing multi-stage decision problems

Figure 2.1: A diagram showing all realisations for the problem

Figure 2.2: The decision tree for the problem

Note that a decision tree is merely a graphical representation of a multi-

2.3 Solving multi-stage decision problems

2.4 Sensitivity analysis

strategy C remains optimal is

range = max p la , p ld , min p ha , p hd .

Consider the probability value p = 0.7 for a proposal on capacity expan-

2.5 Value of information

Expected value of perfect information

much is the advise of such an expert worth to the production manager?

Do not ask the