0% found this document useful (0 votes)
383 views

Practice Problems - Decision Analysis

This document contains 5 practice problems involving decision analysis and decision trees. The problems involve making choices under uncertainty, calculating expected values, and determining optimal policies using techniques like Bayes' rule, maximum expected value, and minimax regret. Key steps include formulating the decision problem, drawing the decision tree, finding posterior probabilities and payoffs, and applying procedures like backward induction to identify the best course of action.

Uploaded by

asaq
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
383 views

Practice Problems - Decision Analysis

This document contains 5 practice problems involving decision analysis and decision trees. The problems involve making choices under uncertainty, calculating expected values, and determining optimal policies using techniques like Bayes' rule, maximum expected value, and minimax regret. Key steps include formulating the decision problem, drawing the decision tree, finding posterior probabilities and payoffs, and applying procedures like backward induction to identify the best course of action.

Uploaded by

asaq
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Practice Problems

Q1. Hank is an intelligent student and usually makes good grades, provided that he can review the
course material the night before the test. For tomorrow’s test, Hank is faced with a small problem: His
fraternity brothers are having an all-night party in which he would like to participate. Hank has three
options:

𝑎𝑎1 = Party all night.

𝑎𝑎2 = Divide the night equally between studying and partying.

𝑎𝑎3 = Study all night.

Tomorrow’s exam can be easy (𝑠𝑠1 ), moderate (𝑠𝑠2 ), or tough (𝑠𝑠3 ), depending on the professor’s
unpredictable mood. Hank anticipates the following scores:
𝑠𝑠1 𝑠𝑠2 𝑠𝑠3

𝑎𝑎1 85 60 40
𝑎𝑎2 92 85 81
𝑎𝑎3 100 88 82
Recommend a course of action for Hank (based on each of the criteria: Maximin, Maximax, Hurwicz
(𝛼𝛼 = 0.5), Minimax Regret). (Answer: Maximin: Study all night; Maximax: Study all night; Hurwicz (𝛼𝛼 =
0.5): Study all night; Minimax Regret: Study all night).

Q2. Vincent Cuomo is the credit manager for the Fine Fabrics Mill. He is currently faced with the
question of whether to extend $100,000 credit to a potential new customer, a dress manufacturer.
Vincent has three categories for the credit-worthiness of a company: poor risk, average risk, and good
risk, but he does not know which category fits this potential customer. Experience indicates that 20
percent of companies similar to this dress manufacturer are poor risks, 50 percent are average risks,
and 30 percent are good risks. If credit is extended, the expected profit for poor risks is −$15,000, for
average risks $10,000, and for good risks $20,000. If credit is not extended, the dress manufacturer
will turn to another mill. Vincent is able to consult a credit-rating organization for a fee of $5,000 per
company evaluated. For companies whose actual credit record with the mill turns out to fall into each
of the three categories, the following table shows the percentages that were given each of the three
possible credit evaluations by the credit-rating organization.

Actual Credit Record

Credit Evaluation Poor Average Good

Poor 50% 40% 20%

Average 40% 50% 40%

Good 10% 10% 40%

a) Develop a decision analysis formulation of this problem by identifying the alternative actions, the
states of nature, and the payoff table when the credit-rating organization is not used.

b) Assuming the credit-rating organization is not used, use Bayes’ decision rule to determine which
decision alternative should be chosen. (Answer: Extend credit with expected payoff= $8,000.)
c) Find EVPI. Does this answer indicate that consideration should be given to using the credit-rating
organization? (Answer: 𝐸𝐸𝐸𝐸𝐸𝐸𝐸𝐸 = $3,000, No)

d) Assume now that the credit-rating organization is used. Develop a probability tree diagram to find
the posterior probabilities of the respective states of nature for each of the three possible credit
evaluations of this potential customer. (Partial answer:
12
𝑃𝑃(𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆 = 𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔|𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓 = 𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔) =
19
12
𝑃𝑃(𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆 = 𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔|𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓 = 𝑎𝑎𝑎𝑎𝑎𝑎𝑎𝑎𝑎𝑎𝑎𝑎𝑎𝑎) =
45
6
𝑃𝑃(𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆 = 𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔|𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓𝑓 = 𝑝𝑝𝑝𝑝𝑝𝑝𝑝𝑝) =
36

Q3. Silicon Dynamics has developed a new computer chip that will enable it to begin producing and
marketing a personal computer if it so desires. Alternatively, it can sell the rights to the computer chip
for $15 million. If the company chooses to build computers, the profitability of the venture depends
upon the company’s ability to market the computer during the first year. It has sufficient access to
retail outlets that it can guarantee sales of 10,000 computers. On the other hand, if this computer
catches on, the company can sell 100,000 machines. For analysis purposes, these two levels of sales
are taken to be the two possible outcomes of marketing the computer, but it is unclear what their
prior probabilities are. If the decision is to go ahead with producing and marketing the computer, the
company will produce as many chips as it finds it will be able to sell, but not more. The cost of setting
up the assembly line is $6 million. The difference between the selling price and the variable cost of
each computer is $600.
a) Develop a decision analysis formulation of this problem by identifying the decision alternatives,
the states of nature, and the payoff table.
b) Develop a graph that plots the expected payoff for each of the decision alternatives versus the
prior probability of selling 10,000 computers.
c) Referring to the graph developed in part (b), find the crossover point. Explain the significance of
this point. (Ans: The expected profit for Build and Sell is the same when 𝒑𝒑 = 𝟎𝟎. 𝟕𝟕𝟕𝟕. They should
build when 𝒑𝒑 ≤ 𝟎𝟎. 𝟕𝟕𝟕𝟕 and sell if 𝒑𝒑 ≥ 𝟎𝟎. 𝟕𝟕𝟕𝟕).
d) Develop a graph that plots the expected payoff (when using Bayes’ decision rule) versus the prior
probability of selling 10,000 computers.
e) Assuming the prior probabilities of the two levels of sales are both 0.5, which decision alternative
should be chosen?

Q4. You are given the following payoff table (in units of thousands of dollars) for a decision analysis
problem:

State of Nature

Alternatives S1 S2 S3

A1 6 1 1

A2 1 3 0

A3 4 1 2
Prior probability 0.3 0.4 0.3
a) According to Bayes’ decision rule, which alternative should be chosen? (Ans: Choose A1 with
expected payoff $2500)
b) Find EVPI (Ans: $1.1 thousand).
c) You are given the opportunity to spend $1,000 to obtain more information about which state of
nature is likely to occur. Given your answer to part (b), might it be worthwhile to spend this
money? (Since the information will cost $1,000 and the value is $1,100, it might be worthwhile to
spend the money).

Q5. Vincent Cuomo is the credit manager for the Fine Fabrics Mill. He is currently faced with the
question of whether to extend $100,000 credit to a potential new customer, a dress manufacturer.
Vincent has three categories for the credit-worthiness of a company: poor risk, average risk, and good
risk, but he does not know which category fits this potential customer. Experience indicates that 20
percent of companies similar to this dress manufacturer are poor risks, 50 percent are average risks,
and 30 percent are good risks. If credit is extended, the expected profit for poor risks is -$15,000, for
average risks $10,000, and for good risks $20,000. If credit is not extended, the dress manufacturer
will turn to another mill. Vincent is able to consult a credit-rating organization for a fee of $5,000 per
company evaluated. For companies whose actual credit record with the mill turns out to fall into each
of the three categories, the following table shows the percentages that were given each of the three
possible credit evaluations by the creditrating organization.
Actual Credit Record

Credit Evaluation Poor Average Good

Poor 6 1 1

Average 1 3 0

Good 4 1 2

a) Develop a decision analysis formulation of this problem by identifying the decision alternatives,
the states of nature, and the payoff table when the credit-rating organization is not used.
b) Assuming the credit-rating organization is not used, use Bayes’ decision rule to determine which
decision alternative should be chosen (Choose to extend credit with expected payoff $ 8000).
c) Find EVPI. Does this answer indicate that consideration should be given to using the credit-rating
organization? (EVPI = $3000).
d) Assume now that the credit-rating organization is used. Develop a probability tree diagram to find
the posterior probabilities of the respective states of nature for each of the three possible credit
evaluations of this potential customer.
e) Draw and properly label the decision tree. Include all the payoffs but not the probabilities.
f) Find the probabilities for the branches emanating from the event nodes.
g) Apply the backward induction procedure, and identify the resulting optimal policy.

You might also like