SUPPLEMENT TO CHAPTER 1

Operational Decision-Making
Tools: Decision Analysis
I N THI S SUPPLEMENT, YOU WILL At the operational level hundreds of decisions are made in order to
LE A RN AB OUT . . . achieve local outcomes that contribute to the achievement of a compa-
ny’s overall strategic goal. These local outcomes are usually not mea-
• Decision Analysis (With and Without sured directly in terms of profit, but instead are measured in terms
of quality, cost-effectiveness, efficiency, productivity, and so forth.
Probabilities)
Achieving good results for local outcomes is an important objective
for individual operational units and individual operations managers.
However, all these decisions are interrelated and must be coordinated
for the purpose of attaining the overall company goals. Decision mak-
ing is analogous to a great stage play or opera, in which all the actors,
the costumes, the props, the music, the orchestra, and the script must
be choreographed and staged by the director, the stage managers,
the author, and the conductor so that everything comes together for
the performance.
For many topics in operations management, there are quantita-
tive models and techniques available that help managers make deci-
sions. Some techniques simply provide information that the operations
manager might use to help make a decision, while other techniques
recommend a specific decision to the manager. Some techniques are
specific to a particular aspect of operations management; others are
more generic and can be applied to a variety of decision-making catego-
ries. These different models and techniques are the “tools” of the oper-
ations manager. Simply having these tools does not make someone an
effective operations manager, just as owning a saw and a hammer does
not make someone a carpenter. An operations manager must know
how to use decision-making tools. How these tools are used in the deci-
sion-making process is an important and necessary part of the study
of operations management. In this supplement and others throughout
this book, we examine several different aspects of operational decision
making using these tools.

Decision Analysis With and ­Without

Probabilities
Decision analysis A set of
In this supplement, we demonstrate a quantitative technique called decision analysis for quantitative decision-making
decision-making situations in which uncertainty exists. Decision analysis is a generic tech- techniques for decision situations
nique that can be applied to a number of different types of operational decision-making areas. in which uncertainty exists.

32
   Decision Analysis With and ­Without Probabilities 33

TAB L E S 1. 1 Payoff Table

States of Nature
Decision a b
1 Payoff 1a Payoff 1b
2 Payoff 2a Payoff 2b

Many decision-making situations occur under conditions of uncertainty. For example,

the demand for a product may not be 100 units next week but may vary between 0 and 200
units, depending on the state of the market, which is uncertain. Decision analysis is a set of
quantitative decision-making techniques to aid the decision maker in dealing with a deci-
sion situation in which there is uncertainty. However, the usefulness of decision analysis for
decision making is also a beneficial topic to study because it reflects a structured, systematic
approach to decision making that many decision makers follow intuitively without ever con-
sciously thinking about it. Decision analysis represents not only a collection of decision-mak-
ing techniques but also an analysis of logic underlying decision making.

Decision Making Without Probabilities

A decision-making situation includes several components—the decisions themselves and the
events that may occur in the future, known as states of nature. Future states of nature may be
high or low demand for a product or good or bad economic conditions. At the time a decision
is made, the decision maker is uncertain which state of nature will occur in the future and has
no control over these states of nature.
When probabilities can be assigned to the occurrence of states of nature in the future, the
situation is referred to as decision making under risk. When probabilities cannot be assigned to
the occurrence of future events, the situation is called decision making under uncertainty. We
discuss the latter case next.
To facilitate the analysis of decision situations, they are organized into payoff tables. A Payoff table A method for
payoff table is a means of organizing and illustrating the payoffs from the different decisions, organizing and illustrating the
given the various states of nature, and has the general form shown in Table S1.1. payoffs from different decisions
Each decision, 1 or 2, in Table S1.1 will result in an outcome, or payoff, for each state of given various states of nature.
nature that will occur in the future. Payoffs are typically expressed in terms of profit, revenues, Payoff The outcome of the
or cost (although they may be expressed in terms of a variety of quantities). For example, if decision.
decision 1 is to expand a production facility and the state of nature a is “good” economic con-
ditions, payoff 1a could be $100,000 in profit.
Once the decision situation has been organized into a payoff table, several criteria are
available to reflect how the decision maker arrives at a decision, including maximax, maxi-
min, minimax regret, Hurwicz, and equal likelihood. These criteria reflect different degrees
of decision-maker conservatism or liberalism. On occasion they result in the same decision;
however, they often yield different results. These decision-making criteria are demonstrated
by the following example:

E XAMPLE S1.1 Decision-Making Criteria Under Uncertainty

The Southern Textile Company is contemplating the future of one of its plants located in South
Carolina. Three alternative decisions are being considered: (1) Expand the plant and produce
lightweight, durable materials for possible sale to the military, a market with little foreign com-
petition; (2) maintain the status quo at the plant, continuing production of textile goods that are
subject to heavy foreign competition; or (3) sell the plant now. If one of the first two alternatives is
chosen, the plant will still be sold at the end of the year. The amount of profit that could be earned
by selling the plant in a year depends on foreign market conditions, including the status of a trade
embargo bill in Congress. The following payoff table describes this decision situation.
34 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

States of Nature

Good Foreign Poor Foreign

Decision Competitive Conditions Competitive Conditions
Expand $800,000 $500,000

Maintain status quo 1,300,000 −150,000

Sell now   320,000   320,000

Determine the best decision using each of the decision criteria.

1. Maximax
2. Maximin
3. Minimax regret
4. Hurwicz
5. Equal likelihood

Solution:

1. Maximax
The decision is selected that will result in the maximum of the maximum payoffs. This is how
Maximax criterion   A decision this criterion derives its name—the maximum of the maxima. The maximax criterion is very
criterion that results in the optimistic. The decision maker assumes that the most favorable state of nature for each decision
maximum of the maximum alternative will occur. Thus, for this example, the company would optimistically assume that good
payoffs. competitive conditions will prevail in the future, resulting in the following maximum payoffs and
decisions:

Expand: $800,000
Status quo: 1,300,000 Maximum
Sell: 320,000

Decision: Maintain status quo

2. Maximin
Maximin criterion A decision The maximin criterion is pessimistic. With the maximin criterion, the decision maker se-
criterion that results in the maxi- lects the decision that will reflect the maximum of the minimum payoffs. For each decision alter-
mum of the minimum payoffs. native, the decision maker assumes that the minimum payoff will occur; of these, the maximum
is selected as follows:

Expand: $500,000 Maximum

Status quo: −150,000
Sell: 320,000

Decision: Expand

Minimax regret criterion   A 3. Minimax Regret Criterion

decision criterion that results in The decision maker attempts to avoid regret by selecting the decision alternative that mini-
the minimum of the maximum mizes the maximum regret. A decision maker first selects the maximum payoff under each state
regrets for each alternative. of nature; then all other payoffs under the respective states of nature are subtracted from these
amounts, as follows:

Good Competitive Conditions Poor Competitive Conditions

$1,300,000 − 800,000 = 500,000 $500,000 − 500,000 = 0

1,300,000 − 1,300,000 = 0 500,000 − (−150,000) = 650,000

1,300,000 − 320,000 = 980,000 500,000 − 320,000 = 180,000

These values represent the regret for each decision that would be experienced by the decision
maker if a decision were made that resulted in less than the maximum payoff. The maximum
   Decision Analysis With and ­Without Probabilities 35

regret for each decision must be determined, and the decision corresponding to the minimum of
these regret values is selected as follows:

Expand: $500,000 Minimum

Status quo: 650,000
Sell: 980,000

Decision: Expand

4. Hurwicz
A compromise is made between the maximax and maximin criteria. The decision maker is
neither totally optimistic (as the maximax criterion assumes) nor totally pessimistic (as the max-
imin criterion assumes). With the Hurwicz criterion, the decision payoffs are weighted by a Hurwicz criterion A decision
­coefficient of optimism, a measure of the decision maker’s optimism. The coefficient of opti- criterion in which the decision
mism, defined as α, is between 0 and 1 (i.e., 0 < α < 1.0). If α = 1.0, the decision maker is complete- payoffs are weighted by a
ly optimistic; if α = 0, the decision maker is completely pessimistic. (Given this definition, 1 − α is coefficient of optimism, α.
the coefficient of pessimism.) For each decision alternative, the maximum payoff is multiplied by α
Coefficient of optimism (α)
and the minimum payoff is multiplied by 1 − α. For our investment example, if α equals .3 (i.e., the
A measure of a decision maker’s
company is slightly optimistic) and 1 − α = .7, the following decision will result:
optimism, from 0 (completely
Expand: $800,000(0.3) + 500,000(0.7) = $590,000 Maximum pessimistic) to 1 (completely
Status quo: 1,300,000(0.3) − 150,000(0.7) = 285,000 optimistic).
Sell: 320,000(0.3) + 320,000(0.7) = 320,000

Decision: Expand

5. Equal Likelihood
The equal likelihood (or Laplace) criterion weights each state of nature equally, thus Equal likelihood (Laplace)
assuming that the states of nature are equally likely to occur. Since there are two states of nature criterion Decision criterion
in our example, we assign a weight of 0.50 to each one. Next, we multiply these weights by each in which each state of nature is
payoff for each decision and select the alternative with the maximum of these weighted values. weighted equally.

Expand: $800,000(0.50) + 500,000(0.50) = $650,000 Maximum

Status quo: 1,300,000(0.50) − 150,000(0.50) = 575,000
Sell: 320,000(0.50) + 320,000(0.50) = 320,000

Decision: Expand
The decision to expand the plant was designated most often by four of the five decision
c­ riteria. The decision to sell was never indicated by any criterion. This is because the payoffs for
expansion, under either set of future economic conditions, are always better than the payoffs for
selling. Given any situation with these two alternatives, the decision to expand will always be
made over the decision to sell. The sell decision alternative could have been eliminated from con-
sideration under each of our criteria. The alternative of selling is said to be dominated by the alter-
native of expanding. In general, dominated decision alternatives can be removed from the payoff
table and not considered when the various decision-making criteria are applied, which reduces the
complexity of the decision analysis.

Different decision criteria often result in a mix of decisions. The criteria used and the
resulting decisions depend on the decision maker. For example, the extremely optimistic deci-
sion maker might disregard the preceding results and make the decision to maintain the status
quo, because the maximax criterion reflects his or her personal decision-making philosophy.

Decision Analysis With Excel

Throughout this book we will demonstrate how to solve quantitative models using the computer
with Microsoft Excel spreadsheets. Exhibit S1.1 shows the Excel spreadsheet solutions for the
different decision-making criteria in Example S1.1. The call-out boxes displayed on and around
the spreadsheet define the cell formulas used to compute the criteria values. For example, the
spreadsheet formula used to compute the maximum payoff value for the decision to “Expand,”
=MAX(C6:D6), is embedded in cell E6 and is also shown on the toolbar at the top of the spread-
sheet. The formula for the Maximax decision, =MAX(E6:E8), is embedded in cell C10.
36 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

E X HIBIT S1.1

=MIN(C8:D8)

=MAX(F6:F8)

=MAX(G7:H7)

=C19*E7+C20*F7

=.5*E8+.5*F8

The Excel file for Exhibit S1.1 and the Excel files for all of the exhibits in the subsequent
chapters in this text are contained on the text website. Students and instructors can download
this file to see how the spreadsheet was constructed as well as the individual cell formulas.
This spreadsheet can also be used as a guideline or template to solve the homework problems
at the end of the chapter using Excel.

Decision Analysis with OM Tools

OM Tools is an Excel-based software package published by Wiley that was specifically designed
for use with this text. It includes solution modules for most of the quantitative techniques in
this text. After downloading OM Tools, modules can be selected by clicking on the “OM Tools”
button on the toolbar at the top of the page, which provides a drop-down list of modules, and
then clicking on the specific module you want to use. In this case we want to use the “Decision
Analysis” module with “Decision Making Under Uncertainty.” A window for providing the
initial problem data, including the problem name and the number of decision alternatives and
states of nature, will then be displayed. Exhibit S1.2 shows the OM Tools Excel spreadsheet
for Example S1.1 with all of the problem data input into the cells. Notice that the difference
between this spreadsheet and the one in Exhibit S1.1 is that the spreadsheet has already been
set up with all of the Excel formulas for the various decision criteria in the cells. Thus, all you
have to do to solve the problem is type in the problem data.

Decision Making With Probabilities

For the decision-making criteria we just used we assumed no available information regarding
the probability of the states of nature. However, it is often possible for the decision maker to
know enough about the future states of nature to assign probabilities that each will occur,
   Decision Analysis With and ­Without Probabilities 37

E X HIBIT S1.2

Input alpha, label the decisions and states of nature, and input
the values for each decision given a particular state of nature.

which is decision making under conditions of risk. The most widely used decision-making Expected value A weighted
criterion under risk is expected value, computed by multiplying each outcome by the proba- average of decision outcomes
bility of its occurrence and then summing these products according to the following formula: in which each future state of
nature is assigned a probability
n
​EV​(x)​= ​∑​p​(​xi​​)​​xi​​ of occurrence.
i=1

where

xi = outcome i
p(xi) = probability of outcome i

E XAMPLE S1.2 Expected Value

Assume that it is now possible for the Southern Textile Company to estimate a probability of .70
that good foreign competitive conditions will exist and a probability of .30 that poor conditions
will exist in the future. Determine the best decision using expected value.

Solution:

The expected values for each decision alternative are computed as follows:

EV(expand) = $800,000(0.70) + 500,000(0.30) = $710,000

EV(status quo) = 1,300,000(0.70) − 150,000(0.30) = 865,000 Maximum

EV(sell) = 320,000(0.70) + 320,000(0.30) = 320,000

The decision according to this criterion is to maintain the status quo, since it has the highest
expected value.
The Excel spreadsheet solution for Example S1.2 is shown in Exhibit S1.3. Note that the values
contained in cells D6, D7, and D8 were computed using the expected value formulas embedded in
these cells. For example, the formula for cell D6 is shown on the formula bar on the Excel screen.
38 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

E X HIBIT S1.3

Formula for expected

value computed in
cell D6

Expected Value of Perfect Information

Occasionally, additional information is available or can be purchased regarding future events,
enabling the decision maker to make a better decision. For example, a company could hire an
economic forecaster to determine more accurately the economic conditions that will occur in the
future. However, it would be foolish to pay more for this information than it stands to gain in extra
profit from having the information. The information has some maximum value that is the limit of
what the decision maker would be willing to spend. This value of information can be computed
Expected value of perfect as an expected value—hence its name, the expected value of perfect information (EVPI).
information (EVPI) To compute the expected value of perfect information, first look at the decisions under
The maximum value of each state of nature. If information that assured us which state of nature was going to occur
perfect information to the (i.e., perfect information) could be obtained, the best decision for that state of nature could
decision maker. be selected. For example, in the textile company example, if the company executives knew
for sure that good competitive conditions would prevail, they would maintain the status quo.
If they knew for sure that poor competitive conditions will occur, then they would expand.
The probabilities of each state of nature (i.e., .70 and .30) indicate that good competitive
conditions will prevail 70% of the time and poor competitive conditions will prevail 30% of the
time (if this decision situation is repeated many times). In other words, even though perfect
information enables the investor to make the right decision, each state of nature will occur
only a certain portion of the time. Thus, each of the decision outcomes obtained using perfect
information must be weighted by its respective probability:

$1,300,000(0.70) + (500,000) (0.30) = $1,060,000

The amount of $1,060,000 is the expected value of the decision given perfect information, not
the expected value of perfect information. The expected value of perfect information is the
maximum amount that would be paid to gain information that would result in a decision
better than the one made without perfect information. Recall from Example S1.2 that the
expected-value decision without perfect information was to maintain the status quo and the
expected value was $865,000.
The expected value of perfect information is computed by subtracting the expected value
without perfect information from the expected value given perfect information:

EVPI = expected value given perfect information − expected value

without perfect information

For our example, the EVPI is computed as

EVPI = $1,060,000 − 865,000 = $195,000

The expected value of perfect information, $195,000, is the maximum amount that the inves-
tor would pay to purchase perfect information from some other source, such as an economic
   Decision Analysis With and ­Without Probabilities 39

forecaster. Of course, perfect information is rare and is usually unobtainable. Typically, the
decision maker would be willing to pay some smaller amount, depending on how accurate
(i.e., close to perfection) the information is believed to be.

Sequential Decision Trees

Sequential decision tree
A payoff table is limited to a single decision situation. If a decision requires a series of deci- A graphical method for analyzing
sions, a payoff table cannot be created, and a sequential decision tree must be used. We decision situations that require a
demonstrate the use of a decision tree in the following example. sequence of decisions over time.

E XAMPLE S1.3 A Sequential Decision Tree

The Southern Textile Company is considering two alternatives: to expand its existing production
operation to manufacture a new line of lightweight material or to purchase land on which to con-
struct a new facility in the future. Each of these decisions has outcomes based on product market
growth in the future that result in another set of decisions (during a 10-year planning horizon), as
shown in the following figure of a sequential decision tree. In this figure the square nodes repre-
sent decisions, and the circle nodes reflect different states of nature and their probabilities.
The first decision facing the company is whether to expand or buy land. If the company
expands, two states of nature are possible. Either the market will grow (with a probability of .60)
or it will not grow (with a probability of .40). Either state of nature will result in a payoff. On the
other hand, if the company chooses to purchase land, three years in the future another decision
will have to be made regarding the development of the land.

Market growth $2,000,000

.60
Expand 2
(–$800,000) .40
No market $225,000
growth Market
Expand growth $3,000,000
.80
(–$800,000) 6
1 Market .20 $700,000
growth (3 years, 4 No market
$0 payoff) growth
Purchase Sell land $450,000
land .60
(–$200,000) 3 Market
.40 Warehouse growth
.30 $2,300,000
(–$600,000) 7
No market .70 $1,000,000
5 No market
growth (3 years, growth
$0 payoff) $210,000
Sell land

At decision node 1, the decision choices are to expand or to purchase land. Notice that the
costs of the ventures ($800,000 and $200,000, respectively) are shown in parentheses. If the plant
is expanded, two states of nature are possible at probability node 2: The market will grow, with a
probability of .60, or it will not grow or will decline, with a probability of .40. If the market grows,
the company will achieve a payoff of $2,000,000 over a 10-year period. However, if no growth
­occurs, a payoff of only $225,000 will result.
If the decision is to purchase land, two states of nature are possible at probability node 3.
These two states of nature and their probabilities are identical to those at node 2; however, the pay-
offs are different. If market growth occurs for a three-year period, no payoff will occur, but the com-
pany will make another decision at node 4 regarding development of the land. At that point, either
the plant will be expanded at a cost of $800,000 or the land will be sold, with a payoff of $450,000.
The decision situation at node 4 can occur only if market growth occurs first. If no market growth
occurs at node 3, there is no payoff, and another decision situation becomes necessary at node 5:
A warehouse can be constructed at a cost of $600,000 or the land can be sold for $210,000. (Notice
that the sale of the land results in less profit if there is no market growth than if there is growth.)
If the decision at decision node 4 is to expand, two states of nature are possible: The market may
grow, with a probability of .80, or it may not grow, with a probability of .20. The probability of market
growth is higher (and the probability of no growth is lower) than before because there has already
40 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

been growth for the first three years, as shown by the branch from node 3 to node 4. The payoffs for
these two states of nature at the end of the 10-year period are $3,000,000 and $700,000, respectively.
If the company decides to build a warehouse at node 5, two states of nature can occur: Market
growth can occur, with a probability of .30 and an eventual payoff of $2,300,000, or no growth can
occur, with a probability of .70 and a payoff of $1,000,000. The probability of market growth is low
(i.e., .30) because there has already been no market growth, as shown by the branch from node
3 to node 5.

Solution:

We start the decision analysis process at the end of the decision tree and work backward toward a
decision at node 1.
First, we must compute the expected values at nodes 6 and 7:

EV(node 6) = 0.80($3,000,000) + 0.20($700,000) = $2,540,000

EV(node 7) = 0.30(2,300,000) + 0.70($1,000,000) = $1,390,000

These expected values (as well as all other nodal values) are shown in boxes in the figure.

$1,290,000 Market
growth $2,000,000
.60
2
.40
Expand $225,000
No market
(–$800,000)
growth
Market
$2,540,000
Expand growth $3,000,000
1 $1,160,000 .80
$1,740,000 (–$800,000) 6
Market .20 $700,000
growth (3 years, 4 No market
Purchase $0 payoff) growth
land Sell land $450,000
(–$200,000)
.60
3 Market
.40 $1,390,000
Warehouse growth $2,300,000
$1,360,000 .30
$790,000 (–$600,000) 7
.70 $1,000,000
No market No market
growth (3 years, 5 growth
$0 payoff) $210,000
Sell land

At decision nodes 4 and 5, a decision must be made. As with a normal payoff table, the deci-
sion is made that results in the greatest expected value. At node 4 the choice is between two values:
$1,740,000, the value derived by subtracting the cost of expanding ($800,000) from the expected
payoff of $2,540,000, and $450,000, the expected value of selling the land computed with a proba-
bility of 1.0. The decision is to expand, and the value at node 4 is $1,740,000.
The same process is repeated at node 5. The decisions at node 5 result in payoffs of $790,000
(i.e., $1,390,000 − 600,000 = $790,000) and $210,000. Since the value $790,000 is higher, the deci-
sion is to build a warehouse.
Next, the expected values at nodes 2 and 3 are computed:

EV(node 2) = 0.60($2,000,000) + 0.40($225,000) = $1,290,000

EV(node 3) = 0.60($1,740,000) + 0.40($790,000) = $1,360,000

(Note that the expected value for node 3 is computed from the decision values previously deter-
mined at nodes 4 and 5.)
Now the final decision at node 1 must be made. As before, we select the decision with the
greatest expected value after the cost of each decision is subtracted.

Expand: $1,290,000 − 800,000 = $490,000

Land: $1,360,000 − 200,000 = $1,160,000

Since the highest net expected value is $1,160,000, the decision is to purchase land, and the payoff
of the decision is $1,160,000.

Decision trees allow the decision maker to see the logic of decision making by providing
a picture of the decision process. Decision trees can be used for problems more complex than
this example without too much difficulty.
  Solved Problems 41

Summary
In this supplement we have provided a general overview of decision operational decisions throughout the organization is interrelated to
analysis. To a limited extent, we have also shown that the logic of such achieve strategic goals.

Key Terms
coefficient of optimism (α) A measure of a expected value of perfect information payoff The outcome of a decision.
decision maker’s optimism, from 0 (completely (EVP) The maximum value that a decision payoff table A method of organizing and
pessimistic) to 1 (completely optimistic), used maker would be willing to pay for perfect infor- illustrating the payoffs from different decisions
in the Hurwicz decision criterion. mation about future states of nature. given various states of nature.
decision analysis A set of quantitative deci- Hurwicz criterion A decision criterion in sequential decision tree A graphical method
sion-making techniques to aid the decision which the decision payoffs are weighted by a for analyzing decision situations that require a
maker in dealing with decision situations in coefficient of optimism, α. sequence of decisions over time.
which uncertainty exists. maximax criterion A decision criterion that
equal likelihood (Laplace) criterion A results in the maximum of the maximum payoffs.
decision criterion in which each state of nature maximin criterion A decision criterion that
is weighted equally. results in the maximum of the minimum payoffs.
expected value A weighted average of deci- minimax regret criterion A decision crite-
sion outcomes in which each future state of rion that results in the minimum of the maxi-
nature is assigned a probability of occurrence. mum regrets for each alternative.

Key Formulas
Expected Value Expected Value of Perfect Information
n
​EV​(x)​ = ​∑​p​(​xi​​)​​xi​​ EVPI = expected value given perfect information − expected value
i=1
without perfect information

Solved Problems
Consider the following payoff table for three product decisions (A, Solution
B, and C) and three future market conditions (payoffs = $ millions):
Step 1. Maximax criterion

Maximum Payoffs
Market Conditions
A $2.0 Maximum
Decision 1 2 3 B 1.2
A $1.0 $2.0 $0.5 C 1.7

B 0.8 1.2 0.9 Decision: Product A

C 0.7 0.9 1.7 Step 2. Maximin criterion

Maximum Payoffs
Determine the best decision using the following decision criteria:
1. Maximax A 0.5
2. Maximin B 0.8 Maximum
C 0.7

Decision: Product B
42 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

Problems
S1.1. Telecomp is a U.S.-based manufacturer of cellular telephones.
Interest Rates
It is planning to build a new manufacturing and distribution facility
in either South Korea, China, Taiwan, Poland, or Mexico. The cost of Project Decline Stable Increase
the facility will differ between countries and will even vary within
countries depending on the economic and political climate, including Office building 0.5 1.7 4.5
monetary exchange rates. The company has estimated the facility cost Parking lot 1.5 1.9 2.4
(in $ millions) in each country under three different future economic/
political climates as follows: Warehouse 1.7 1.4 1.0

Shopping mall 0.7 2.4 3.6

Economic/Political Climate Condominiums 3.2 1.5 0.6

Country Decline Same Improve S1.4. In Problem S1-3 the Landloc real estate development firm has
hired an economist to assign a probability to each direction interest
South Korea 21.7 19.1 15.2
rates may take over the next five years. The economist has determined
that there is a .50 probability that interest rates will decline, a .40 prob-
China 19.0 18.5 17.6
ability that rates will remain stable, and a .10 probability that rates
Taiwan 19.2 17.1 14.9 will increase.
a. Using expected value, determine the best project.
Poland 22.5 16.8 13.8
b. Determine the expected value of perfect information.
Mexico 25.0 21.2 12.5 S1.5. Nicole Nelson has come into an inheritance from her grand-
parents. She is attempting to decide among several investment
alternatives. The return after one year is dependent primarily on
Determine the best decision using the following decision criteria.
the interest rate during the next year. The rate is currently 7%, and
(Note that since the payoff is cost, the maximax criterion becomes
she anticipates it will stay the same or go up or down by at most
minimin and maximin becomes minimax.)
2 points. The various investment alternatives plus their returns
a. Minimin ($10,000s) given the interest rate changes are shown in the follow-
b. Minimax ing table:
c. Hurwicz (α = .40)
d. Equal likelihood Interest Rates

S1.2. A global economist hired by Telecomp, the U.S.-based computer Investments 5% 6% 7% 8% 9%

manufacturer in Problem S1-1, estimates that the probability that the Money market fund 1.7 2.8 3.0 3.6 4.5
economic and political climate overseas and in Mexico will decline
during the next five years is .30, the probability that it will remain Stock growth fund −5 −3 3.5 5 7.5
approximately the same is .40, and the probability that it will improve Bond fund 5 4 3.5 3 2
is .30. Determine the best country to construct the new facility in and
the expected value of perfect information. Government fund 4 3.6 3.2 2.8 2.1

S1.3. Landloc, a real estate development firm, is considering sev- Risk fund −12 −7 4.2 9.3 16.7
eral alternative development projects. These include building and
Savings bonds 3 3 3.2 3.4 3.5
leasing an office building, purchasing a parcel of land and building
a parking lot, buying and leasing a warehouse, building a shop-
Determine the best investment using the following decision criteria:
ping mall, and building and selling condominiums. The financial
success of these projects depends on interest rate movement in a. Maximax
the next five years. The various development projects and their b. Maximin
five-year financial return ($ millions) given that interest rates will c. Equal likelihood
decline, remain stable, or increase are shown in the following pay-
off table. S1.6. In Problem S1-5 assume that Nicole, with the help of a financial
Determine the best investment using the following decision criteria: newsletter and some library research, has been able to assign probabili-
ties to each of the possible interest rates during the next year as follows:
a. Maximax
b. Maximin
Interest Rate 5% 6% 7% 8% 9%
c. Equal likelihood
Probability .1 .2 .4 .2 .1
d. Hurwicz (α = .3)
  Problems 43

a. Using expected value, determine her best investment decision. Determine the best decision using each of the following criteria:
b. Nicole is considering hiring a financial analyst to help her a. Minimin
determine the best investment. What is the maximum amount
b. Minimax
she should pay an analyst?
c. Equal likelihood
S1.7. Leevi Starch, an apparel company with a global supply chain, is
d. Minimax regret
adding a new supplier for several new styles of its denim jeans, and
the suppliers it’s considering are in China, India, the Philippines, Bra- S1.10. Telecomp in Problem S1-9 estimates that the probabilities of
zil, and Mexico. A major factor in the company’s decision is transpor- the severity of events in each of the countries are as follows:
tation and shipping costs, which are dependent on future oil prices.
The following payoff table summarizes the total monthly costs (in
$100,000s), including manufacturing and shipping costs for the sup- Event Severity
pliers in each of the countries given the future state of oil prices.
Supplier Country Low Moderate High
Oil Prices China .43 .45 .12
Supplier Decrease Same Increase India .56 .33 .11
China $2.7 $3.9 $6.3
Thailand .37 .41 .22
India 2.1 3.8 6.5
Philippines .47 .46 .07
Philippines 1.7 4.3 6.1
Brazil 3.5 4.5 5.7 Determine the best decision for Telecomp using expected value.
Mexico 4.1 5.1 5.4 S1.11. The Dynamax Company is going to introduce one of three new
products: a widget, a hummer, or a nimnot. The market conditions
Determine the best decision using each of the following criteria: (favorable, stable, or unfavorable) will determine the profit or loss the
a. Minimin company realizes, as shown in the following payoff table:
b. Minimax
c. Equal likelihood Market Conditions
d. Minimax regret Product Favorable .2 Stable .5 Unfavorable .3
S1.8. Leevi Starch in Problem S1-7 estimates that the probabilities of Widget $160,000 $90,000 −$50,000
future global changes in oil prices are .09 that they will decrease, .27
that they will remain the same, and .64 that they will decrease. Hummer    70,000 40,000    20,000
a. Determine the best supplier for the company using expected
value. Nimnot    45,000 35,000    30,000

b. If the company wants to hire an energy analyst to help it deter-

mine more accurately what future oil prices will do, what is the a. Compute the expected value for each decision and select the
maximum amount it should pay the analyst? best one.
b. Determine how much the firm would be willing to pay to a
S1.9. Telecomp, a computer manufacturer with a global supply market research firm to gain better information about future
chain, is adding a new supplier for some of its component parts, market conditions.
and the suppliers it’s considering are in China, India, Thailand,
c. Assume that probabilities cannot be assigned to future market
and the Philippines. As part of its risk management program Tele-
conditions, and determine the best decision using the maximax,
comp wants to assess the possible impact of a supplier shutdown
maximin, minimax regret, and equal likelihood criteria.
in the event of a natural disaster, such as a flood, fire, or an earth-
quake. The following payoff table summarizes Telecomp’s losses
S1.12. John Wiley & Sons, Inc. publishes an operations management
(in millions of dollars) for supplier shutdowns given different lev-
textbook that is scheduled for a revision. The book has been mod-
els of event severity:
erately successful, but each year more new books enter the market,
some existing books are dropped by publishers, and various innovative
Event Severity pedagogical approaches are introduced by authors and publishers, so
that the competitive market is always highly uncertain. In addition,
Supplier Country Low Moderate High the role that the Internet will play in future textbook publishing is an
China $8 $11 $21 unknown. As a result, Wiley is trying to decide whether to publish
the next edition of the OM book as a smaller paperback, publish a
India 6 7 14 new edition very similar in size and content to the current edition,
significantly revise the book with an emphasis on services and pro-
Thailand 3 12 17 cesses, or make a major revision with significant physical changes,
Philippines 5 9 15 including adding color and more graphics. The following payoff table
summarizes the possible revision decisions with profits (or losses) for
44 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

the three-year lifecycle of the new edition, and the future states of Determine the best decision using each of the following criteria:
nature relative to the competitive market: a. Maximax
b. Maximin
Competitive Market
Publication c. Equal likelihood
Decision Unfavorable Same Favorable d. Hurwicz (α = .65)
Paperback   $68,000 $170,000 $395,000 e. Minimax regret

Similar revision     24,000 375,000 672,000 S1.15. In Problem S1-14, suppose Amtrex is able to assign probabilities
to each of the states of nature for each of the suppliers/ports as follows:
Major content     31,000 515,000 725,000
revision States of Nature
Major physical −105,000 280,000 972,000 Declining Same Growth
revision Decision Conditions Conditions Conditions

Determine the best decision for the publisher using the following criteria: Hong Kong .27 .45 .28

a. Maximax Singapore .18 .51 .31

b. Minimax Shanghai .22 .61 .17
c. Equal likelihood
Busan .15 .45 .40
d. Hurwicz (α = .35)
Kaohsiung .25 .38 .37
S1.13. In Problem S1-12, if Wiley is able to assign probabilities of
occurrence of .23 to unfavorable market conditions, .46 for the same a. Using expected value, determine the port/supplier Amtrex
market conditions, and .31 for favorable market conditions, what is should use.
the best decision using expected value? Based on the results in Prob-
b. Based on the results from Problem S1-14, and the result from
lem S1-12 and the expected value result in this problem, does there
part a, is there a best overall decision?
appear to be an overall “best” decision? Compute the expected value
of perfect information, and explain its meaning. S1.16. The Willow Café is located in an open-air mall. Its lease
S1.14. Amtrex International is a major U.S.-based electronics firm expires this year and the restaurant owner has the option of signing a
that manufactures a number of electronic components for domestic 1-, 2-, 3-, 4-, or 5-year lease. However, the owner is concerned about
and global consumer electronics companies. It imports most of its recent energy price increases (including the price of gasoline), which
materials and the components used in its products to the United States affect virtually every aspect of the restaurant operation, including the
from overseas suppliers. Amtrex is in the process of trying to improve price of food items and materials, delivery costs, and its own utilities.
its global supply chain operations, and as part of this process the com- The restaurant was very profitable when energy prices were lower,
pany wants to determine a single supplier located at one of the major and the owner believes if prices remain at approximately their cur-
ports around the world to contract with for the majority of its busi- rent level profits will still be satisfactory; however, if prices continue
ness. The company is considering six suppliers, each located at one to rise he believes that he might be forced to close. In these latter
of the following ports: Hong Kong, Singapore, Shanghai, Busan, and circumstances a longer-term lease could be a financial disaster, but
Kaohsiung. The company has estimated the possible profit (or loss) with a shorter-term lease the mall landlord could always rent the
it might achieve with each of the potential suppliers depending on a restaurant’s space out from under it when the lease expires. Thus, the
variety or possible future company and port conditions, including IT restaurant owner’s estimates of future profits must also reflect the
capability, port growth and expansion, ship and container availabil- possibility that the lease will not be renewable. The following pay-
ity, security, regional market and political environment, and transport off table summarizes the owner’s profit (and loss) estimates for each
to the port from the supplier’s suppliers. Depending on these various future state of nature of energy prices (over a five-year period):
factors, further supplier and port conditions could decline, grow and
expand, or remain the same. The following payoff table summarizes Energy Prices
the increased outcomes (in $ millions) for the potential suppliers and
the possible future states of nature for a specific time frame: Lease Decrease Same Increase
Decision .17 .34 .49
States of Nature 1-year $156,000 $93,000 $16,000

Declining Same Growth 2-year 427,000 150,000 −42,000

Decision Conditions Conditions Conditions 3-year 642,000 319,000 −171,000
Hong Kong −$31 $28 $67 4-year 933,000 473,000 −337,000
Singapore −24 33 71 5-year 1,228,000 516,000 −551,000

Shanghai −28 35 55
a. Determine the best decision using expected value.
Busan −17 25 49 b. Compute the expected value of perfect information for the
Willow Café. Explain what this value means and how such infor-
Kaohsiung −15 41 59
mation might be obtained.
  Problems 45

S1.17. The Weight Club (see Case Problem 1.3) is considering adding a. The market must decide how many apples to order in a week.
a new service facility among several possible alternatives, including a Construct a payoff table for this decision situation and determine
child care center, a swimming pool, new locker rooms and showers, a the amount of apples that should be ordered using expected value.
health-oriented food court, and a spa. The success of each alternative b. Assuming that probabilities cannot be assigned to the demand
depends on their demand (i.e., new members who would join because values, what would the best decision be using the maximax and
of the new facility), which is uncertain. The following payoff table sum- maximin criteria?
marizes the returns (based on costs and increased enrollments) for each
alternative service facility given three future levels of demand: S1.20. The manager of the greeting card section of Harvey’s
Department Store is considering her order for a particular line of
Demand holiday cards. The cost of each box of cards is $3; each box will be
sold for $5 during the holiday season. After the holiday season, the
Service Facility Poor Moderate High cards will be sold for $2 a box. The card section manager believes
Child care center $17,000 $27,000 $41,000 that all leftover cards can be sold at that price. The estimated
demand during the holiday season for the cards, with associated
Swimming pool −75,000 26,000 71,000 probabilities, is as follows:
New lockers and showers 12,000 37,000 57,000
Demand (boxes) Probability
Food court −31,000 19,000 87,000
25 .10
Spa 6,000 25,000 32,000
26 .15
Determine the best decision for the club using the following criteria:
27 .30
a. Maximax
28 .20
b. Minimax
c. Hurwicz (α = .45) 29 .15
d. Equal likelihood 30 .10
S1.18. In Problem S1.17, assume the Weight Club is able to estimate
probabilities of occurrence for each possible future demand state, as a. Develop the payoff table for this decision situation and compute
follows: the expected value for each alternative and identify the best decision.
b. Compute the expected value of perfect information.
Demand S1.21. Assume that the probabilities of demand in Problem S1-20 are
Service Facility Poor Moderate High no longer valid; the decision situation is now one without probabili-
ties. Determine the best number of cards to stock using the following
Child care center .12 .54 .34 decision criteria:
Swimming pool .24 .63 .13 a. Maximin
b. Maximax
New lockers and .09 .44 .47
showers c. Hurwicz (α = .4)
d. Minimax regret
Food court .18 .74 .08
S1.22. Zarax, a global apparel company, is adding a new supplier for
Spa .31 .48 .21
denim fabric that it uses to manufacture denim jeans, and the sup-
pliers it’s considering are located near the ports of Shanghai, Mum-
Determine the best decision using expected value.
bai, Manila, Santos, and Veracruz. A major factor in the company’s
S1.19. The Midtown Market purchases apples from a local grower. decision is transportation and shipping costs, which are dependent
The apples are purchased on Monday at $2.00 per pound, and the on several factors, including port traffic, container costs, and future
market sells them for $3.00 per pound. Any apples left over at the oil prices. The following payoff table summarizes the total monthly
end of the week are sold to a local zoo for $0.50 per pound. The shipping costs (in $1 millions) for the suppliers in each of the ports
possible demands for apples and the probability for each are as given the future state of related logistics costs.
follows:
Logistics Costs
Demand (lb) Probability
Port Decrease Same Increase
20 .10
Shanghai $2.7 $3.9 $6.3
21 .20
22 .30 Mumbai 2.1 3.8 6.5

23 .30 Manila 1.7 4.3 6.1

24 .10 Santos 3.5 4.5 5.7

1.00 Veracruz 4.1 5.1 5.4

46 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

Determine the best decision using each of the following criteria:

Subcontract
a. Minimin
b. Minimax Outcomes Probability Profit (millions)
c. Equal likelihood Moderate success 1 $250
d. Minimax regret

S1.23. Zarax in problem S1.22 estimates that the probabilities of The cost of preparing the contract proposal is $2,000,000. If the com-
future changes in global logistics are .09 that they will decrease, .27 pany does not make a bid, it will invest in an alternative venture with
that they will remain the same, and .64 that they will increase. Deter- a guaranteed profit of $30 million. Construct a sequential decision
mine the best supplier for the company using expected value. tree for this decision situation and determine whether the company
should make a bid.
S1.24. If Zarax in problems S1.22 and S1.23 wants to hire a supply
chain analyst to help it determine more accurately what future logis- S1.27. The director of career advising at Grand Valley Community
tics costs will be, what is the maximum amount they should pay the College wants to use decision analysis to provide information to help
analyst? students decide which two-year degree program they should pursue.
The director has set up the following payoff table for six of the most
S1.25. A machine shop owner is attempting to decide whether to pur-
popular and successful degree programs at GVCC that shows the
chase a new drill press, a lathe, or a grinder. The return from each will
estimated five-year gross income ($) from each degree for four future
be determined by whether the company succeeds in getting a govern-
­economic conditions:
ment military contract. The profit or loss from each purchase and the
probabilities associated with each contract outcome are shown in the
following payoff table. Compute the expected value for each purchase Economic Conditions
and select the best one. Degree
Program Recession Average Good Robust
Contract No Contract Graphic Design $115,000 $155,000 $190,000 $220,000
Purchase .40 .60
Nursing 140,000 175,000 210,000 225,000
Drill press $40,000 $28,000
Real Estate    95,000 135,000 230,000 350,000
Lathe 20,000    4,000
Medical 120,000 180,000 210,000 270,000
Grinder 12,000 10,000 Technology

Culinary    85,000 125,000 180,000 290,000

S1.26. The Extron Oil Company is considering making a bid for a Technology
shale oil development contract to be awarded by the federal govern-
Computer 125,000 160,000 200,000 260,000
ment. The company has decided to bid $110 million. The company
Information
estimates that it has a 60% chance of winning the contract with this
Technology
bid. If the firm wins the contract, it can choose one of three meth-
ods for getting the oil from the shale: It can develop a new method
for oil extraction, use an existing (inefficient) process, or subcontract Determine the best degree program in terms of projected income,
the processing out to a number of smaller companies once the shale using the following decision criteria:
has been excavated. The results from these alternatives are given as a. Maximax
follows:
b. Maximin
c. Equal likelihood
Develop New Process
d. Hurwicz (α = .25)
Outcomes Probability Profit (millions) S1.28. In Problem S1.27 the director of career advising at Grand
Great success .30 $600 Valley Community College has paid a local economic forecasting
firm to indicate a probability for each future economic condition
Moderate success .60 300 over the next five years. The firm estimates that there is a .15 prob-
ability of a recession, a .50 probability that the economy will be
Failure .10 −100 average, a .25 probability that the economy will be good, and a .10
probability that it will be robust. Using expected value, determine
the best degree program in terms of projected income. If you were
Use Present Process the director of career advising, which degree program would you
recommend?
Outcomes Probability Profit (millions)
S1.29. Federated Electronics, Ltd., manufactures display screens
Great success .50 $300 and monitors for computers and televisions that it sells to compa-
nies around the world. It wants to construct a new warehouse and
Moderate success .30 200 distribution center in Asia to serve emerging markets there. It has
Failure .20 −40 identified potential sites in the port cities of Shanghai, ­Singapore,
Pusan, Kaohsiung, and Hong Kong and has estimated the possible
  Problems 47

revenues for each (minus construction costs, which are higher in

some cities like Hong Kong). At each site the projected revenues are Heavy Snows Probability
primarily based on these factors: (1) the economic conditions at the 1 .12
port, including the projected traffic, infrastructure, labor rates and
availability, and expansion and modernization; and (2) the future gov- 2 .19
ernment situation, which includes the political stability, fees, tariffs,
duties, and trade regulations. Following is a payoff table that shows 3 .24
the projected revenues (in $ billions) for six years given the four pos- 4 .22
sible combinations for positive and negative port and government
conditions: 5 .13

6 .08
Port Port Port Port
Negative/ Negative/ Positive/­ Positive/
7 .02
Government Government Government Government
Port Negative Positive Negative Positive 1.00
Shanghai −$0.271 $0.437 $0.523 $1.08
Alex is considering the purchase of a new self-propelled snowblower
Singapore −0.164 0.329 0.441 0.873 for $575 that would allow him, his wife, or his children to clear the
driveway after a snow. Discuss what you think Alex’s decision should
Pusan 0.119 0.526 0.337 0.732
be and why.
Kaoshiung −0.235 0.522 0.226 1.116 S1.32. The management of State Union Bank was concerned about
the potential loss that might occur in the event of a physical catastro-
Hong Kong −0.317 0.256 0.285 1.653
phe such as a power failure or a fire. The bank estimated that the
loss from one of these incidents could be as much as $100 million,
Determine the port city Federated should select for its new distribu-
including losses due to interrupted service and customer relations.
tion center using the following decision criteria:
One project the bank is considering is the installation of an emer-
a. Maximax gency power generator at its operations headquarters. The cost of the
b. Maximin emergency generator is $900,000, and if it is installed no losses from
c. Equal likelihood this type of incident will be incurred. However, if the generator is not
installed, there is a 10% chance that a power outage will occur during
d. Hurwicz (α = .55) the next year. If there is an outage, there is a .04 probability that the
S1.30. In Problem S1.29 Federated Electronics, Ltd. has hired a Wash- resulting losses will be very large, or approximately $90 million in lost
ington, D.C.-based global trade research firm to assess the probabili- earnings. Alternatively, it is estimated that there is a .96 probability of
ties of each combination of port and government conditions for the only slight losses of around $2 million. Using decision tree analysis,
five ports. The research firm probability estimates for the five ports determine whether the bank should install the new power generator.
are as follows: S1.33. Allegheny Mountain Power and Light is an electric utility com-
pany with a large fleet of vehicles, including automobiles, light trucks,
Port Port Port Port and construction equipment. The company is evaluating four alterna-
Negative/ Negative/ Positive/­ Positive/ tive strategies for maintaining its vehicles at the lowest cost: (1) take
Government Government Government Government no preventive maintenance at all and repair vehicle components when
Port Negative Positive Negative Positive they fail; (2) take oil samples at regular intervals and perform whatever
Shanghai .09 .27 .32 .32 preventive maintenance is indicated by the oil analysis; (3) change the
vehicle oil on a regular basis and perform repairs when needed; and
Singapore .05 .22 .22 .51 (4) change the oil at regular intervals and take oil samples regularly,
performing maintenance repairs as indicated by the sample analysis.
Pusan .08 .36 .27 .29 For autos and light trucks, strategy 1 (no preventive maintenance)
Kaoshiung .11 .12 .46 .31 costs nothing to implement and results in two possible outcomes:
There is a .08 probability that a defective component will occur, requir-
Hong Kong .10 .23 .30 .37 ing emergency maintenance at a cost of $1600, or there is a .92 proba-
bility that no defects will occur and no maintenance will be necessary.
(a) Using expected value, determine the best port to construct Strategy 2 (take oil samples) costs $40 to implement (i.e., take a
the distribution center. sample), and there is a .08 probability that there will be a defective part
and a .92 probability that there will not be a defect. If there is actually a
(b) Using any decision criterion, determine the port you think
defective part, there is a .70 probability the sample will correctly iden-
would be the best location for the distribution center, and justify
tify it, resulting in preventive maintenance at a cost of $500. However,
your answer.
there is a .30 probability that the sample will not identify the defect and
S1.31. Alex Mason has a wide-curving, uphill driveway leading to indicate everything is okay, resulting in emergency maintenance later
his garage. When there is a heavy snow, Alex hires a local carpenter, at a cost of $1600. On the other hand, if there are actually no defects,
who shovels snow on the side in the winter, to shovel his driveway. there is a .20 probability that the sample will erroneously indicate that
The snow shoveler charges $30 to shovel the driveway. Following there is a defect, resulting in unnecessary maintenance at a cost of
is a probability distribution of the number of heavy snows each $250. There is a .80 probability that the sample will correctly indicate
winter: there are no defects, resulting in no maintenance and no costs.
48 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

Strategy 3 (changing the oil regularly) costs $34.80 to implement jury will award her a lesser amount of $1,000,000, of which Mary
and has two outcomes: a .04 probability of a defective component, would get $500,000.
which will require emergency maintenance at a cost of $1600, and a Using decision-tree analysis, decide if Mary should sue the man-
.96 probability that no defects will occur, resulting in no maintenance ufacturer.
and no cost.
S1.37. State University has three healthcare plans for its faculty and
Strategy 4 (changing the oil and sampling) costs $54.80 to imple-
staff to choose from, as follows.
ment and results in the same probabilities of defects and no defects
as strategy 3. If there is a defective component, there is a .70 probabil- Plan 1—monthly cost of $32 with a $500 deductible: the partic-
ity that the sample will detect it and $500 in preventive maintenance ipants pay the first $500 of medical payments for the year, the
costs will be incurred. Alternatively, there is a .30 probability that the insurer pays 90% of all remaining expenses.
sample will not detect the defect, resulting in emergency maintenance
Plan 2—monthly cost of $5 but a deductible of $1200, with the
at a cost of $1600. If there is no defect, there is a .20 probability the
insurer paying 90% of medical expenses after the insured pays
sample will indicate there is a defect, resulting in an unnecessary
the first $1200 in a year.
maintenance cost of $250, and a .80 probability that the sample will
correctly indicate no defects, resulting in no cost. Plan 3—monthly cost of $24 with no deductible; the participants
Develop a decision strategy for Allegheny Mountain Power and pay 30% of all expenses with the remainder paid by the insurer.
Light and indicate the expected value of this strategy.1
Tracy McCoy, an administrative assistant in the management
S1.34. In Problem S1.33, the decision analysis is for automobiles and department, estimates that her annual medical expenses are defined
light trucks. Allegheny Mountain Power and Light would like to refor- by the following probability distribution:
mulate the problem for its heavy construction equipment. Emergency
maintenance is much more expensive for heavy equipment, costing
$15,000. Required preventive maintenance costs $2000 and unneces- Annual Medical Expenses Probability
sary maintenance costs $1200. The cost of an oil change is $200 and $100 .15
the cost of taking an oil sample and analyzing it is $50. All the proba-
bilities remain the same. Determine the strategy the company should 500 .30
use for its heavy equipment.
1,500 .35
S1.35. Tech is playing State in the last conference game of the season.
Tech is trailing State 21 to 14 with 7 seconds left in the game, when 3,000 .10
they score a touchdown. Still trailing 21 to 20, Tech can either go for
two points and win or go for one point to send the game into overtime. 5,000 .05
The conference championship will be determined by the outcome of 10,000 .05
this game. If Tech wins they will go to the Sugar Bowl, with a payoff of
$9.2 million; if they lose they will go to the Gator Bowl, with a payoff
of $1.5 million. If Tech goes for two points there is a 30% chance they Determine which medical plan Tracy should select.
will be successful and win (and a 70% chance they will fail and lose). S1.38. The Orchard Wine Company purchases grapes from one of
If they go for one point there is a .98 probability of success and a tie two nearby growers each season to produce a particular red wine. It
and a .02 probability of failure. If they tie they will play overtime, in purchases enough grapes to produce 3000 bottles of the wine. Each
which Tech believes they have only a 20% chance of winning because grower supplies a certain portion of poor-quality grapes that will
of fatigue. result in a percentage of bottles being used as fillers for cheaper table
a. Use decision-tree analysis to determine if Tech should go for wines according to the following probability distribution:
one point or two points.
b. What would Tech’s probability of winning the game in over- Probability of %
time have to be to make Tech indifferent between going for one Defective
point or two points?
Percentage Defective Grower A Grower B
S1.36. Mary Decker is suing the manufacturer of her car because
of a defect that she believes caused her to have an accident and 2 .12 .26
kept her out of work for a year. She is suing the company for
$3.5 million. The company has offered her a settlement of $700,000, 4 .21 .34
of which Mary would receive $600,000 after attorneys’ fees. Her
6 .26 .22
attorney has advised her that she has a 50% chance of winning her
case. If she loses she will incur attorneys’ fees and court costs of 8 .31 .10
$75,000. If she wins she is not guaranteed her full requested settle-
ment. Her attorney believes that if she wins, there is a 50% chance 10 .10 .08
she could receive the full settlement, in which case Mary would get
$2 million after her attorney takes his cut, and a 50% chance that the The two growers charge a different price for their grapes and because
of differences in taste, the company charges different prices for their
1
This problem is based on J. Mellichamp, D. Miller, and O-J. Kwon, “The wine depending on which grapes they use. The annual profit from the
Southern Company Uses a Probability Model for Cost Justification of Oil Sam- wine produced from each grower’s grapes for each percentage defec-
ple Analysis,” Interfaces 23 (3; May-June 1993), pp. 118–124. tive is as follows:
  Case Problems 49

areas or bypass the test market and introduce the product nationally.
Profit The cost of the test market is $150,000. If the company conducts the
Defective Grower A Grower B test market, it must wait to see the results before deciding whether
or not to introduce the salad dressings nationally. The probability of
2% $44,200 $42,600 a positive test market result is estimated to be .6. Alternatively, the
company cannot conduct the test market and make the decision to
4 40,200 40,300
introduce the dressings or not. If the salad dressings are introduced
6 36,200 38,000 nationally and are a success, the company estimates it will realize
an annual profit of $1,600,000, while if the dressings fail it will incur
8 32,200 35,700 a loss of $700,000. The company believes the probability of success
for the salad dressings is .50 if they are introduced without the test
10 28,200 33,400
market. If the company does conduct the test market and it is posi-
tive, the probability of successfully introducing the salad dressings
Use decision-tree analysis to determine from which grower the com-
increases to .8. If the test market is negative and the company intro-
pany should purchase grapes.
duces the salad dressings anyway, the probability of success drops
S1.39. Huntz Food Products is attempting to decide if it should to .30.
introduce a new line of salad dressings called Special Choices. The Using decision-tree analysis, determine if the company should
company can test market the salad dressings in selected geographic conduct the test market.

Case Problems
Case Problem S1.1 Whither an MBA at Strutledge? could increase exposure and visibility for the school and enhance its
reputation, as a whole, which could also result in increased enroll-
Strutledge (see Case Problem 1.3) is a small liberal arts college faced ments and revenue sources. The cost to establish and maintain each
with rising costs and decreasing enrollments. It would like to increase new program differs according to faculty salaries, facilities, and the
revenues (including tuition, donations, and grants) by expanding support necessary to attract new students, which, in turn, affects rev-
its student base and building ties with businesses in the surround- enues. The degree of success that each new graduate program might
ing area. To do so, it is considering establishing a new graduate achieve is affected by competition from other colleges and universities
program—an MBA, a master’s in computer science, a master’s in and the ability of a program to attract new faculty and students. The
information technology, a master’s in nursing (affiliated with a major following payoff table summarizes the possible gains (i.e., revenues
hospital in a nearby urban area), or a master’s in healthcare adminis- less costs) the college might realize with each new program under
tration. In addition to generating additional enrollments within a new different future success scenarios.
program, administrators also believe that a new graduate program

Program Success

Moderate Very
Graduate Program Unsuccessful Success Successful Successful
MBA −$316,000 −$57,000 $231,000 $424,000

Computer Science −210,000 −35,000 190,000 375,000

Information Technology −472,000 −75,000 305,000 517,000

Nursing −135,000 81,000 205,000 307,000

Health Administration −75,000 55,000 180,000 245,000

Determine the best decision for the college using the following criteria: f. Strutledge has estimated probabilities of occurrence for the
a. Maximax different states of program success as shown in the following
table. What is the best decision using expected value?
b. Maximin
g. Based on these decision analysis results, what would you rec-
c. Equal likelihood
ommend that Strutledge College’s decision be?
d. Hurwicz (α = .50)
h. What decision would you recommend to Strutledge? Explain
e. If Strutledge administrators use the Hurwicz criterion to your reasons.
make their decision, explain what this might mean about their
­decision-making strategy.
50 S UP P L E M E N T 1 Operational Decision-Making Tools: Decision Analysis

Program Success
Moderate Very
Graduate Program Unsuccessful Success Successful Successful
MBA .32 .35 .24 .09
Computer Science .38 .41 .16 .05
Information Technology .25 .33 .30 .12
Nursing .17 .28 .41 .14
Health Administration .08 .34 .47 .11

the form of a decision tree that identifies the different decision points
Transformer Replacement at
Case Problem S1.2
in the development process from the initial decision to invest in a
Mountain States Electric Service project’s development through the actual commercialization of the
final product.
Mountain States Electric Service is an electrical utility company
The first decision point in the development process is whether or
serving several states in the Rocky Mountain region. It is consider-
not to fund a proposed project for one year. If the decision is no, then
ing replacing some of its equipment at a generating substation and is
there is no resulting cost; if the decision is yes, then the project pro-
attempting to decide whether it should replace an older, existing PCB
ceeds at an incremental cost to the company. The company establishes
transformer. (PCB is a toxic chemical known formally as polychlori-
specific short-term, early technical milestones for its projects after one
nated biphenyl.) Even though the PCB generator meets all current
year. If the early milestones are achieved, the project proceeds to the
regulations, if an incident occurred, such as a fire, and PCB contam-
next phase of project development; if the milestones are not achieved,
ination caused harm either to neighboring businesses or farms or to
the project is abandoned. In its planning process, the company devel-
the environment, the company would be liable for damages. Recent
ops probability estimates of achieving and not achieving the early
court cases have shown that simply meeting utility regulations does
milestones. If the early milestones are achieved, then the project is
not relieve a utility of liability if an incident causes harm to others.
funded for further development during an extended time frame spe-
Also, courts have been awarding large damages to individuals and
cific to a project. At the end of this time frame, a project is evaluated
businesses harmed by hazardous incidents.
according to a second set of (later) technical milestones. Again the
If the utility replaces the PCB transformer, no PCB incidents will
company attaches probability estimates for achieving and not achiev-
occur, and the only cost will be that of the transformer, $85,000. Alter-
ing these later milestones. If the late milestones are not achieved, the
natively, if the company decides to keep the existing PCB transformer,
project is abandoned.
then management estimates there is a 50-50 chance of there being
If the late milestones are achieved, this means that technical
a high likelihood of an incident or a low likelihood of an incident.
uncertainties and problems have been overcome and the company
For the case in which there is a high likelihood that an incident will
next assesses the project’s ability to meet its strategic business
occur, there is a .004 probability that a fire will occur sometime during
objectives. At this stage the company wants to know if the eventual
the remaining life of the transformer and a .996 probability that no
product coincides with the company’s competencies and if there
fire will occur. If a fire occurs, there is a .20 probability that it will
appears to be an eventual clear market for the product. It invests in
be bad and the utility will incur a very high cost of approximately
a product “prelaunch” to ascertain the answers to these questions.
$90 million for the cleanup, whereas there is a .80 probability that the
The outcomes of the prelaunch are that either there is a strategic
fire will be minor and a cleanup can be accomplished at a low cost of
fit or there is not, and the company assigns probability estimates
approximately $8 million. If no fire occurs, then no cleanup costs will
to each of these two possible outcomes. If there is not a strategic
occur. For the case in which there is a low likelihood of an incident
fit at this point, the project is abandoned and the company loses
occurring, there is a .001 probability that a fire will occur during the
its investment in the prelaunch process. If it is determined that
life of the existing transformer and a .999 probability that a fire will
there is a strategic fit, then three possible decisions result. (1) The
not occur. If a fire does occur, then the same probabilities exist for the
company can invest in the product’s launch and a successful or
incidence of high and low cleanup costs, as well as the same cleanup
unsuccessful outcome will result, each with an estimated probabil-
costs, as indicated for the previous case. Similarly, if no fire occurs,
ity of occurrence. (2) The company can delay the product’s launch
there is no cleanup cost.
and at a later date decide whether to launch or abandon. (3) If
Perform a decision-tree analysis of this problem for Mountain States
it launches later, then the outcomes are success or failure, each
Electric Service and indicate the recommended solution. Is this the deci-
with an estimated probability of occurrence. Also, if the product
sion you believe the company should make? Explain your reasons.
launch is delayed, there is always a likelihood that the technology
Source: This case was adapted from W. Balson, J. Welsh, and D. Wilson, “Using will become obsolete or dated in the near future, which tends to
Decision Analysis and Risk Analysis to Manage Utility Environmental Risk,” reduce the expected return.
Interfaces 22 (6) (November–December 1992), pp. 126–139. The table provides the various costs, event probabilities, and
investment outcomes for five projects the company is considering.
Determine the expected value for each project and then rank the
Case Problem S1.3 Evaluating Projects at Nexcom projects accordingly for the company to consider.
Systems
Source: This case was adapted from R. K. Perdue, W. J. McAllister, P. V. King,
Nexcom Systems develops information technology systems for com- and B. G. Berkey, “Valuation of R and D Projects Using Options Pricing and
mercial sale. Each year it considers and evaluates a number of differ- Decision Analysis Models,” Interfaces 29, (6) (November–December 1999), pp.
ent projects to undertake. It develops a road map for each project in 57–74.
  References 51

Project

Decision Outcomes/Event 1 2 3 4 5
Fund—1 year $200,000 380,000 270,000 230,000 400,000

P(Early milestones—yes) .72 .64 .84 .56 .77

P(Early milestones—no) .28 .36 .16 .44 .23

Long-term funding $690,000 730,000 430,000 270,000 350,000

P(Late milestones—yes) .60 .56 .65 .70 .72

P(Late milestones—no) .40 .44 .35 .30 .28

Prelaunch funding $315,000 420,000 390,000 410,000 270,000

P(Strategic fit—yes) .80 .75 .83 .67 .65

P(Strategic fit—no) .20 .25 .17 .33 .35

P(lnvest—success) .60 .65 .70 .75 .83

P(lnvest—failure) .40 .35 .30 .25 .17

P(Delay—success) .80 .70 .65 .80 .85

P(Delay—failure) .20 .30 .35 .20 .15

Invest—success $7,300,000 8,200,000 4,700,000 5,200,000 3,800,000

Invest—failure −2.000,000 −3,500,000 −1,500,000 −2,100,000 −900,000

Delay—success 4,500,000 6,000,000 3,300,000 2,500,000 2,700,000

Delay—failure −1,300,000 −4,000,000 −800,000 −1,100,000 −900,000

References
Holloway, C. A. Decision Making Under Uncertainty. Englewood Von Neumann, J., and O. Morgenstern. Theory of Games and Eco-
Cliffs, NJ: Prentice Hall, 1979. nomic Behavior, 3rd ed. Princeton, NJ: Princeton University Press,
Howard, R. A. “An Assessment of Decision Analysis.” Operations 1953.
Research 28 (1; January–February 1980), pp. 4–27. Williams, J. D. The Complete Strategist, rev. ed. New York: McGraw-
Keeney, R. L. “Decision Analysis: An Overview.” Operations Research Hill, 1966.
30 (5; September–October 1982), pp. 803–838.
Luce, R. D., and H. Raiffa. Games and Decisions. New York: John
Wiley, 1957.