May the key to your success rest not in your professional skills or personal charisma; rather, may the

dynamic of your strength lay in the presence and power of God.

Time is precious, but we do not know yet how precious it really is. We will only know wh

Decision Theory
Introduction
A decision may be defined as the process of choosing an action (solution) to a problem from a set of
feasible alternatives. In choosing the optimal solution, it means we have a set of possible other solutions. In
decision theory, the focus is on the process of finding the action yielding the best results. Statistical
decision theory is concerned with which decision from a set of feasible alternatives is optimal for a
particular set of conditions.
In many situations, selection of a course of action is vital especially where the situation being considered
has a significant monetary or social impact and is accompanied by some degree of uncertainty. Under this
situation, decision theory becomes an important analytical tool that can be used to provide a favorable
approach to the selection of a particular course of action.
Decision analysis utilizes the concept of gain and loss (profit & cost) associated with every possible action
the decision-maker can select. Nearly all facets/fields of life require decision-making e.g. marketing,
production, finance, etc.

Example (marketing Decision Problem) A motor company must decide whether to purchase assembled
door locks for the new vehicle model or manufacture & assemble the parts at their plant. If the sales of the
new model continue to increase, it will be profitable to manufacture & assemble the parts. However, if the
sales level continue to decrease, it will be more profitable to purchase already assembled parts. Which
decision should the management make?

Elements of a Decision
There are 3 elements or components for any decision-making situation. They include:-
1. The alternatives/actions/decisions-They are the choices available to the decision-maker and they are
assured to be mutually exclusive and exhaustive events.
 The decision-maker has control over the alternatives.
2. States of nature:-These are uncontrollable future events that affect the outcome of a decision.
 They are outside the control of the decision-maker and are also assured to be mutually exclusive &
exhaustive. Eg. In the above example, the company doesn’t know if the demand will be high or low.
3. Pay offs:- In decision analysis, we refer to the consequence resulting from a specific combination of a
decision alternative and a state of nature as a payoff and it measures the net benefit for the decision-
maker. Pay-off can be defined as a quantitative measure of the value of the outcome of an action.
Note If an action does not involve risk, the pay-off will be the same regardless of which state of nature
occurs.
Decision Making Environment
Selection of a terminal (final) decision is mainly influenced by the state of nature surrounding the problem.
Usually, actions & their associated pay-offs are known in advance to their decision-maker. However, the
decision maker does not know which alternative will be the best in each case. He/she knows with certainty
the state of nature that will be in effect.
We have 3 different types of decision-making environments namely:

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 2
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

(i) Decision-making under the environment of certainty

(ii) Decision-making under conditions of risk
(iii) Decision-making under conditions of uncertainty

1. Decision-Making under Conditions of Certainty

This is a situation where the states of nature are known, and if they are not known, they have no influence
on the outcome of the decision. In this case, it is easy for the decision-maker to maximize monetary gains
or any other type of utility. Decision-making under conditions of certainty is straight forward unless the
number of alternatives is very large.
The availability of partial/imperfect information about a problem results in the other two decision-making
environments.

2. Decision-Making under Conditions of Risk

Here the decision-making process is conducted in an environment of risk and the degree of knowledge
associated with each state of nature is unknown. However, an appropriate estimate of the likelihood can
be determined based on a subjective judgment or use of some mathematical relations.

3. Decision-Making under Conditions of Uncertainty

Here, more than one outcome can be render from only a single decision and probabilities can be
associated with values. This complicates the decision making because the decision-maker is constrained
due to lack of knowledge about probabilities or the occurrences of the outcomes of possible course of
action only pay-offs are known and nothing known about the likelihood (probability ) of each state of
nature.
Note Data availability should point certainty & uncertainty about a problem. Risk lies between certainty
and uncertainty.

Pay-off Tables
It’s a table showing payoffs for all combinations of decision alternatives and states of nature
Let A1, A2 ,….., An be the possible actions and S1 , S2 ,…..Sm be the water of state of nature.
Also, let the return associated with action Ai and state of nature Sj be Vij or V(Ai Sj) for i= 1, 2, , ……,n and
J =1,2,……,m Now for each combination of action Ai and state of nature Sj the decision maker knows what
the resulting pay off will be. The following is the possible pay-off
State of Nature
S1 S2 ………. Sm
A1 V11 V12 ………. V1m
Alternatives

A2 V21 V22 ………. V2m

…

… …
… …
… …
… …

… …
… …

……….
…
…

……….
An Vn1 Vn2 ………. Vnm
Prob P(S1) P(S2) ………. P(Sm)
NB pay-offs can either be profits or costs
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 3
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

To use the above pay-off table to reach an optimal action, the state of nature is taken to be a random
variable, an additional element i.e the probability distribution for each state of nature is needed in decision-
making frame-work.

Example 1 Pittsburgh Development Corporation (PDC) has purchased land, which will be the site of a
new luxury condominium complex. The location provides a spectacular view of downtown Pittsburgh and
the Golden Triangle where the Allegheny and Monongahela rivers meet to form the Ohio River. PDC plans
to price the individual condominium units between $300,000 and $1,400,000.
PDC has preliminary architectural drawings for three different-sized projects: one with 30 condominiums,
one with 60 condominiums, and one with 90 condominiums. The financial success of the project depends
upon the size of the condominium complex and the chance event concerning the demand for the
condominiums. The statement of the PDC decision problem is to select the size of the new luxury
condominium project that will lead to the largest profit given the uncertainty concerning the demand for the
condominiums. Given the statement of the problem, it is clear that the decision is to select the best size for
the condominium complex. PDC has the following three decision alternatives:
d1 _ a small complex with 30 condominiums
d2 _ a medium complex with 60 condominiums
d3 _ a large complex with 90 condominiums
A factor in selecting the best decision alternative is the uncertainty associated with the chance event
concerning the demand for the condominiums. When asked about the possible demand for the
condominiums, PDC’s president acknowledged a wide range of possibilities, but decided that it would be
adequate to consider two possible chance event outcomes: a strong demand and a weak demand. For this
PDC problem, the chance event concerning the demand for the condominiums has two states of nature:
s1 _ strong demand for the condominiums
s2 _ weak demand for the condominiums
Thus, management must first select a decision alternative (complex size), then a state of nature follows
(demand for the condominiums), and finally a consequence will occur. In this case, the consequence is the
PDC’s profit.
Given the three decision alternatives and the dollars is shown in Table 2 alongside Note, for
two states of nature, which complex size should example, that if a medium complex is built and
PDC choose? To answer this question, PDC demand turns out to be strong, a profit of $14
will need to know the consequence associated million will be realized.
with each decision alternative and each state of
nature.. Given the three decision alternatives Demand
and the two states of nature, which complex Decision Alternative Strong S1 Weak S2
size should PDC choose? To answer this
Small complex, d1 35 65
question, PDC will need to know the
consequence associated with each decision Medium complex, d2 36 12
alternative and each state of nature. The payoff Large complex, d3 -3 60
table with profits expressed in millions of
Example 2 Company A owns a track of land that contains oil. A consulting geologist has reported to the
company management that she believes that there is one chance in four of land having oil. Due to this
prospect another company B has offered to purchase the land for $90,000. However company A can hold
the land and drill for oil itself. If oil is found the company’s expected profit is $700,000. A loss of $100,000
will be incurred if the land is dry.
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 4
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

The management of company A has 2 possible actions.

A1:- sell the land to company B at $ 90 000
A2:- drill for oil at a cost of $ 100 000, and make a profit of $700 000 if oil is found.
The possible states of nature are state of Nature
S1:- the land contains oil with corresponding Actions S1 S2
probability of 0.25 A1 $90 $90
S2:- the land is dry with corresponding A2 $700 $-100
probability of 0.75 Prior Prob 0.25 0.75
The Pay-off table is as shown alongside:-

Decision Trees
A decision tree graphically shows the sequential nature of the decision-making process.
Figure 1 presents a decision tree for the PDC problem, demonstrating the natural or logical progression that
will occur over time. First, PDC must make a decision regarding the size of the condominium complex (d1,
d2, or d3). Then, after the decision is implemented, either state of nature s1 or s2 will occur. The number at
each end point of the tree indicates the payoff associated with a particular sequence. For example, the
topmost payoff of 8 indicates that an $8 million profit is anticipated if PDC constructs a small
condominium complex (d1) and demand turns out to be strong (s1). The next payoff of 7 indicates an
anticipated profit of $7 million if PDC constructs a small condominium complex (d1) and demand turns out
to be weak (s2). Thus, the decision tree shows graphically the sequences of decision alternatives and states
of nature that provide the six possible payoffs. The decision tree in Figure 2 has four nodes, numbered 1–4,
that represent the decisions and chance events. Squares are used to depict decision nodes and circles are
used to depict chance nodes. Thus, node 1 is a decision node, and nodes 2, 3, and 4 are chance nodes. The
branches leaving the decision node correspond to the decision alternatives. The branches leaving each
chance node correspond to the states of nature. The payoffs are shown at the end of the states-of-nature
branches. We now turn to the question: How can the decision maker use the information in the payoff table
or the decision tree to select the best decision alternative?
Figure 1 Decision Tree for the PDC problem

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 5
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

How to draw
A decision tree is a chronological representation of the decision process/problem. Each decision tree has
two types of nodes; round nodes correspond to the states of nature while square nodes correspond to the
decision alternatives. The branches leaving each round node represent the different states of nature while
the branches leaving each square node represent the different decision alternatives. At the end of each limb
of a tree are the payoffs attained from the series of branches making up that limb.
Note End nodes usually represent the final outcomes of earlier risky outcomes and decisions made in
response
Decision tree software is a relatively new advance that permits users to solve decision analysis problems
with flexibility, power, and ease. Programs such as DPL, Tree Plan, and Supertree allow decision problems
to be analyzed with less effort and in greater depth than ever before.

Example 3 Getz Products Company is investigating the possibility of producing and marketing backyard
storage sheds. Undertake king this project would require the construction of either a large or a small
manufacturing plant. The market for the product produced—storage sheds—could be either favorable or
unfavorable. Getz, of course, has the option of not developing the new product line at all. A decision tree
for this situation is presented in Figure 2 below
Figure 2 A Decision Tree Getz Products Company

Exercise 1
1. Getz Products Company is investigating the possibility of producing and marketing backyard storage
sheds. Undertaking this project would require the construction of either a large or a small
manufacturing plant. The market for the product produced—storage sheds—could be either favorable or
unfavorable. Getz, of course, has the option of not developing the new product line at all. With a
favorable market, a large facility will give Getz Products a net profit of $200,000. If the market is
unfavorable, a $180,000 net loss will occur. A small plant will result in a net profit of $100,000 in a
favorable market, but a net loss of $20,000 will be encountered if the market is unfavorable. Construct a
payoff table, indicating the events and alternative courses of action.
2. You are a marketing manager for a food products company, considering the introduction of a new brand
of organic salad dressings. You need to develop a marketing plan for the salad dressings in which you
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 6
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

must decide whether you will have a gradual introduction of the salad dressings (with only a few
different salad dressings introduced to the market) or a concentrated introduction of the salad dressings
(in which a full line of salad dressings will be introduced to the market). You estimate that if there is a
low demand for the salad dressings, your first year’s profit will be $1 million for a gradual introduction
and -$5 million (a loss of $5 million) for a concentrated introduction. If there is high demand, you
estimate that your first year’s profit will be $4 million for a gradual introduction and $10 million for a
concentrated introduction. Suppose that the probability is 0.60 that there will be low demand, construct a
payoff table for these two alternative courses of action.
3. The DellaVecchia Garden Center purchases and sells Christmas trees during the holiday season. It
purchases the trees for $10 each and sells them for $20 each. Any trees not sold by Christmas day are
sold for $2 each to a company that makes wood chips. The garden center estimates that four levels of
demand are possible: 100, 200, 500, and 1,000 trees. Compute the payoffs for purchasing 100, 200, 500,
or 1,000 trees for each of the four levels of demand. Construct a payoff table, indicating the events and
alternative courses of action. Construct a decision tree.
4. Zed and Adrian and run a small bicycle shop called "Z to A Bicycles". They must order bicycles for the
coming season. Orders for the bicycles must be placed in quantities of twenty (20). The cost per bicycle
is $70 if they order 20, $67 if they order 40, $65 if they order 60, and $64 if they order 80. The bicycles
will be sold for $100 each. Any bicycles left over at the end of the season can be sold (for certain) at $45
each. If Zed and Adrian run out of bicycles during the season, then they will suffer a loss of "goodwill"
among their customers. They estimate this goodwill loss to be $5 per customer who was unable to buy a
bicycle. Zed and Adrian estimate that the demand for bicycles this season will be 10, 30, 50, or 70
bicycles with probabilities of 0.2, 0.4, 0.3, and 0.1 respectively.
5. Finicky's Jewelers sells watches for $50 each. During the next month, they estimate that they will sell
15, 25, 35, or 45 watches with respective probabilities of 0.35, 0.25, 0.20, and ... (figure it out). They can
only buy watches in lots of ten from their dealer. 10, 20, 30, 40, and 50 watches cost $40, 39, 37, 36, and
34 per watch respectively. Every month, Finicky's has a clearance sale and will get rid of any unsold
watches for $24 (watches are only in style for a month and so they have to buy the latest model each
month). Any customer that comes in during the month to buy a watch, but is unable to, costs Finicky's
$6 in lost goodwill. Find the best action under each of the four decision criteria.
6. An author is trying to choose between two publishing companies that are competing for the marketing
rights to her new novel. Company A has offered the author $10,000 plus $2 per book sold. Company B
has offered the author $2,000 plus $4 per book sold. The author believes that five levels of demand for
the book are possible: 1,000, 2,000, 5,000, 10,000, and 50,000 books sold.
a) Compute the payoffs for each level of demand for company A and company B.
b) Construct a payoff table, indicating the events and alternative courses of action.
7. A supermarket chain purchases large quantities of white bread for sale during a week. The stores
purchase the bread for $0.75 per loaf and sell it for $1.10 per loaf. Any loaves not sold by the end of the
week can be sold to a local thrift shop for $0.40. Based on past demand, the probability of various levels
of demand is as follows:
Demand (Loaves) 6,000 8,000 10,000 12,000
Probability 0.10 0.50 0.30 0.10
Construct a payoff table, indicating the events and alternative courses of action.
8. The owner of a company that supplies home heating oil would like to determine whether to offer a solar
heating installation service to its customers. The owner of the company has determined that a start-up
cost of $150,000 would be necessary, but a profit of $2,000 can be made on each solar heating system
installed. The owner estimates the probability of various demand levels as follows: How would your
answers to (a) through (h) be affected if the startup cost were $200,000?
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 7
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

No of Units Installed 50 100 200

Probability 0.40 0.30 0.30
Construct a payoff table, indicating the events and alternative courses of action.

9. H. Weiss, Inc., is considering building a sensitive new airport scanning device. His managers believe
that there is a probability of 0.4 that the ATR Co. will come out with a competitive product. If Weiss
adds an assembly line for the product and ATR Co. does not follow with a competitive product, Weiss’s
expected profit is $40,000; if Weiss adds an assembly line and ATR follows suit, Weiss still expects
$10,000 profit. If Weiss adds a new plant addition and ATR does not produce a competitive product,
Weiss expects a profit of $600,000; if ATR does compete for this market, Weiss expects a loss of
$100,000.
10. Ronald Lau, chief engineer at South Dakota Electronics, has to decide whether to build a new state-of-
the-art processing facility. If the new facility works, the company could realize a profit of $200,000. If it
fails, South Dakota Electronics could lose $180,000. At this time, Lau estimates a 60% chance that the
new process will fail. The other option is to build a pilot plant and then decide whether to build a
complete facility. The pilot plant would cost $10,000 to build. Lau estimates a 50-50 chance that the
pilot plant will work. If the pilot plant works, there is a 90% probability that the complete plant, if it is
built, will also work. If the pilot plant does not work, there is only a 20% chance that the complete
project (if it is constructed) will work. Lau faces a dilemma. Should he build the plant? Should he build
the pilot project and then make a decision?
11. Joseph Biggs owns his own sno-cone business and lives 30 miles from a California beach resort. The
sale of sno-cones is highly dependent on his location and on the weather. At the resort, his profit will be
$120 per day in fair weather, $10 per day in bad weather. At home, his profit will be $70 in fair weather
and $55 in bad weather. Assume that on any particular day, the weather service suggests a 40% chance
of foul weather. Construct Joseph’s pay off table.
12. Kenneth Boyer is considering opening a bicycle shop in North Chicago. Boyer enjoys biking, but this is
to be a business endeavor from which he expects to make a living. He can open a small shop, a large
shop, or no shop at all. Because there will be a 5-year lease on the building that Boyer is thinking about
using, he wants to make sure he makes the correct decision. Boyer is also thinking about hiring his old
marketing professor to conduct a marketing research study to see if there is a market for his services.
The results of such a study could be either favorable or unfavorable. Develop a decision tree for Boyer.
13. Kenneth Boyer (of Problem A.18) has done some analysis of his bicycle shop decision. If he builds a
large shop, he will earn $60,000 if the market is favorable; he will lose $40,000 if the market is
unfavorable. A small shop will return a $30,000 profit with a favorable market and a $10,000 loss if the
market is unfavorable. At the present time, he believes that there is a 50-50 chance of a favorable
market. His former marketing professor, Y. L. Yang, will charge him $5,000 for the market research. He
has estimated that there is a .6 probability that the market survey will be favorable. Furthermore, there is
a .9 probability that the market will be favorable given a favorable outcome of the study. However,Yang
has warned Boyer that there is a probability of only .12 of a favorable market if the marketing research
results are not favorable. Expand the decision tree of Problem A.18 to help Boyer decide what to do.
14. Dick Holliday is not sure what he should do. He can build either a large video rental section or a small
one in his drugstore. He can also gather additional information or simply do nothing. If he gathers
additional information, the results could suggest either a favorable or an unfavorable market, but it
would cost him $3,000 to gather the information. Holliday believes that there is a 50-50 chance that the
information will be favorable. If the rental market is favorable, Holliday will earn $15,000 with a large
section or $5,000 with a small. With an unfavorable video-rental market, however, Holliday could lose
$20,000 with a large section or $10,000 with a small section. Without gathering additional information,
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 8
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

Holliday estimates that the probability of a favorable rental market is .7. A favorable report from the
study would increase the probability of a favorable rental market to .9. Furthermore, an unfavorable
report from the additional information would decrease the probability of a favorable rental market to .4.
Of course, Holliday could ignore these numbers and do nothing. What is your advice to Holliday?
15. Louisiana is busy designing new lottery “scratch-off” games. In the latest game, Bayou Boondoggle, the
player is instructed to scratch off one spot: A, B, or C. A can reveal “Loser,” “Win $1,” or “Win $50.” B
can reveal “Loser” or “Take a Second Chance.” C can reveal “Loser” or “Win $500.” On the second
chance, the player is instructed to scratch off D or E. D can reveal “Loser” or “Win $1.” E can reveal
“Loser” or “Win $10.” The probabilities at A are .9, .09, and .01. The probabilities at B are .8 and .2.
The probabilities at C are .999 and .001. The probabilities at D are .5 and .5. Finally, the probabilities at
E are .95 and .05. Draw the decision tree that represents this scenario. Use proper symbols and label all
branches clearly. Calculate the expected value of this game.

Criteria for Decision-Making under Uncertainty

Here we consider decision-making under the assumptions that no probability distributions are available. The
methods to be presented here include,
a) Optimistic criterion d) Minimax Regret/Savage criterion
b) Conservative/Pessimistic Approach. e) Hurwicz/Realism/Approach
c) Laplace/Equally likely Approach

a) Maximax/Optimistic Approach
The approach would be used by an optimistic decision-maker. Based on this approach we choose the
decision/action with the largest profit if the pay-offs are gains, otherwise, if the pay-offs are costs/losses,
choose the action with the lowest loss/costs. we choose Ai which satisfies.
Max (Max Vij ) if 𝑉𝑖𝑗 are profits Min (Min Vij ) if 𝑉𝑖𝑗 are costs
𝐴𝑖 𝑆𝑗 𝐴𝑖 𝑆𝑗

Example 4 Consider the following problem with two alternatives and two states of nature
. The pay-off table below consists of profits. Solution
State of Nature Maximum
Actions S1 S2 Actions Sj
A1 $20 $6 A1 $20
A2 $25 $3 A2 $25 - maximax
Using the optimistic approach, obtain the Optimal course of action is A2 NB if Vij were costs
optimal course of action. the best course of action would be A1

b) Maximin/ Conservative Approach

Here, we list the minimum pay off for each action (across all the states of nature) and then select the action
corresponding to the maximum of these minimums. This is called ‘maximizing the lowest possible profit
‘However, if the payoffs are in terms of cost, list the maximum costs for each alternative and then select the
action with the lowest maximum (i.e maximum possible cost is minimized). This criterion is based on
making the best out of the worst possible condition, and we choose Ai which satisfies.
Max (Min Vij ) if 𝑉𝑖𝑗 are profits and Min (Max Vij ) if 𝑉𝑖𝑗 are costs
𝐴𝑖 𝑆𝑗 𝐴𝑖 𝑆𝑗

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 9
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

Example 5 Re-do example 1 using the conservative approach. If vij are costs
Solution:
Actions Row Min
A1 $6 - maximin Therefore choose action A1.
A2 $3

c) Laplace Criterion
This criteria is based on the principal of equally likely events. Basically, we average the pay-offs for Ai
over Sj and then pick the action with the highest average. However if the pay-offs are costs, we pick the
action with the lowest average. ie we select Ai which statistics
𝑚 𝑚
1 1
Max {𝑚 ∑ 𝑉𝑖𝑗 } if 𝑉𝑖𝑗 are profits and Min {𝑚 ∑ 𝑉𝑖𝑗 } if 𝑉𝑖𝑗 are costs
𝐴𝑖 𝐴𝑖
𝑗=1 𝑗=1

Example 6 Re-do example 1 using the laplace approach

Solution:
Actions Row Average Choose action A2 as the optimal
A1 $13
A2 $14 - max average

d) Savage Minimax Regret criterion

This approach requires the calculation regret/opportunity loss table as following Let Rij be the regret/loss
incurred by taking action Ai under state Sj .ie
Max Vij – Vij if are profits or gain
𝑆𝑗
R ij = {
Vij − Min Vij if are costs or losses
𝑆𝑗

The table generated by Rij is called regret matrix. Specifically, for each state or nature obtain the difference
between each pay-off and the largest pay-off if pay-offs are gains..Using the regret table, we list the
maximum regret for each possible action and then select the action with the lowest regret. Effectively,
Select Ai such that: Min (Max R ij ) no matter whether 𝑉𝑖𝑗 are profit or costs
𝐴𝑖 𝑆𝑗

Example 7 Redo example 1 using the savage regret criterion.

Solution Since we have profits, the regret matrix R ij = Max Vij – Vij . Regret Table Is as shown below.
𝑆𝑗

state of Nature Maximum

Actions S1 S2 Sj
A1 5 0 5

A2 0 3 3
A2 has the minimax regret therefore it’s the best course of action.

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 10
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

e) Hurwicz /Realism Approach

Also called the weighted average/realism approach; and it’s a compromise between the most optimistic and
the most pessimistic decision. It strikes a balance between extreme optimism and extreme pessimism by
weighing the two conditions using respective weights 𝛼 and 1 − 𝛼 where 0 < 𝛼 < 1. The parameter 𝛼
is called the index of optimism.. Select action Ai that yields:
Max {𝛼 Max Vij + (1 − 𝛼) Min Vij } if 𝑉𝑖𝑗 are profits or gains
𝐴𝑖 𝑆𝑗 𝑆𝑗

Min {𝛼 Min Vij + (1 − 𝛼) Max Vij } if Vij are costsor losses

𝐴𝑖 𝑆𝑗 𝑆𝑗
Note When 𝛼 = 1, the decision-maker is optimistic and if 𝛼 = 0, he/she is pessimistic about the future.

Example 8 Re-do example 1 using hurwicz criterion with 𝛼 = 0.55

Solution:
0.55max +0.45min The best course of action is action A2 since it has
Action Sj Sj the maximum value
A1 0.55(20)+0.45(6)=13.7
A2 0.55(25)+0.45(3)=15.1

Example 9 A recreation facility must decide on the level of supply it must stock to meet the needs of its
customers during one of the holidays. The exact number of customers is unknown but it’s expected to be in
one of the categories 200, 250, 300, or 350. Four levels of supply are
suggested and the payoff table below gives the Category of customers
pay-offs for each combination of the level of S1 S2 S3 S4
stock Ai and the category of customers Sj Use
stock levels

A1 5 10 18 28
all the 5 criterions above (for Hurwicz, use A2 8 7 8 23
𝛼 = 0.4) to find the optimal course of action. A3 21 18 12 21
The values in pay-off table are cost. A4 30 22 17 15
Solu;tion
Action Row Min Row Max Row Average 0.4min +0.6max
A1 5 28 15.25 18.8
A2 7 23 11.5 16.6
A3 12 21 18 17.4
A4 15 30 21 24
a). Optimistic approach (minimum)
Min (Min Vij ) = 5 corresponding to A1 ⇒ A1 is the best course of action
𝐴𝑖 𝑆𝑗
b). Maximum/Conseversative approach.
Min (Max Vij ) = 21 corresponding to A3 ⇒ A3 is the best course of action
𝐴𝑖 𝑆𝑗
Row Average
c).Laplace Criterion Min { S } = 11.5 corresponding to A2 ⇒ A2 is the optimal act
𝐴𝑖 j

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 11
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

d). Hurwicz Criterion See table 1

Min {0.4 Min Vij + 0.6 Max Vij } = 16.6 corresponding to A2 ⇒ A2 is the optimal action
𝐴𝑖 𝑆𝑗 𝑆𝑗
e). Savage Regret approach.
Category of customers Max
S1 S2 S3 S4 Sj
stock levels

A1 o 3 10 13 13
A2 3 0 0 8 8
A3 16 11 4 6 16
A4 25 15 9 0 25
Min (Max R ij ) = 8 corresponding to A2 ⇒ A2 is the optimal act.
𝐴𝑖 𝑆𝑗
Exercise 2
1. For the following payoff table, determine the optimal action based on the maximax, the maximin and the Laplace criterions

a) state of Nature b) state of Nature

Actions S1 S2 Actions S1 S1
A1 50 200 10 2 A1
A2 100 125 -2 8 A2
8 5 A3
2. Obtain the optical decision for the following pay off tables (Vij are profits) using the 5 criterions above
a) State of Nature b) State of Nature
Actions S1 S2 Actions S1 S2 S3
A1 100 0 A1 35 65 5
A2 50 20 A2 36 12 48
A3 -3 60 30

c) State of Nature d) State of Nature

Actions S1 S2 S3 S4 Actions S1 S2 S3 S4
A1 16 9 3 6 A1 12 8 7 3
A2 3 4 2 0 A2 15 9 5 -2
A3 -6 -2 1 0 A3 7 7 7 7
3. Redo to question 2, treating Vij as costs obtain the optimal course of action.
4. A group of friends are planning a recreational outing and have constructed the following payoff table to help
them decide which activity to engage in. Assume that the payoffs represent their level of enjoyment for
each activity under the various weather conditions.
Weather a) If the group is (i) optimistic (ii)
Alternatives Cold Warm Rainy
conservative, what decision should they
make?
Bike: A1 10 8 6
b) If the group chooses to minimize their
Hike: A2 14 15 2 maximum regret, what activity will they
Fish: A3 7 8 9 choose?
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 12
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

5. An investor is considering 4 different opportunities, A, B, C, or D. The payoff for each opportunity will
depend on the economic conditions, represented in the payoff table below.
Economic Condition
Poor S1 Average S2 Good S3 Excellent S4
A 50 75 20 30
Investment

B 80 15 40 50
C -100 300 -50 10
D 25 25 25 25
What decision would be made under each of the five criterions above?
6. .A milk vender must decide the no of casto stock 7. A business owner is trying to decide whether to
using each of the five criterions and the buy, rent, or lease office space and has
following profits pay-off table obtain the best constructed the following payoff table based on
course of action whether business is brisk or slow. using each of
Stock Demand the five criterions, find the optimal strategy for
Milk cases 15 16 17 18
the business owner.
15 39 26 22 18 State of Business
16 22 32 28 24 Alternatives Brisk Slow.
17 14 24 34 30 Buy 90 -10
Rent 70 40
18 6 16 26 36
Lease 60 55

8. The local operations manager for the IRS must Number of Compliance
decide whether to hire 1, 2, or 3 temporary Workers Low Medium High
workers. He estimates that net revenues will 1 50 50 50
vary with how well taxpayers comply with the 2 100 60 20
new tax code. How many new workers will he 3 150 70 -10
hire using each of the five criterions?

Decision-Making under Risk Environment

The problem of decision making under risk is to choose an action (or decision) among many different
available actions which gives (possibly) maximum expected profit or maximum expected revenue or
minimum expected losses or minimum expected costs as the case may be, under uncertain situations.
Under this environment, the decision maker has some knowledge regarding the state of nature and he/she is
able to assign subject probability estimates for each state of nature. Various criterions are involved under
this environment.

a) Most Probable State (or Maximum likelihood) criterion

Identifies the state with the highest prior probability and then selects the action corresponding to the
maximum pay off in this particular state of nature.
Note This criterion ignores some useful information as it only concentrates on the most probable state.
Thus it’s not commonly used

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 13
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

b) Expected Pay-off (Expected Monetary Value) Criterion.

–simply called EMV Criterion
Choose the action that yields maximum expected value. For each action compute
𝑚

EMV(𝐴𝑖 ) = ∑ 𝑝(𝑆𝑗 )𝑉𝑖𝑗

𝑗=1
Criterion: select the alternative Ai that yields
Max{EMV(𝐴𝑖 )} if 𝑉𝑖𝑗 are profits or Min{EMV(𝐴𝑖 )} if 𝑉𝑖𝑗 𝑖 are costs
𝐴𝑖 𝐴𝑖

Example 10 The Robotic Micro computer company manufacturers micro-computers. The company is
contemplating the expansion of its manufacturing facilities. The following table shows this pay-off in
$1,000,000 for the company. Obtain the best decision using the maximum likelihood and EMV criterion.
Demand
Alternatives High Moderate Low
Expand current facility 10 5 -1
Build new facility 25 15 -5
License another manufacturer 15 8 -0.5
Prior Probability 0.4 0.4 0.2
Solution
a) Maximum likelihood Approach.
Most probable state is either high or moderate demand. The best course of action is building a new facility.
b) EMV Criterion EMV (A1 ) =10(0.4) + 5(0.4)-1(0.2)= 5.8
EMV(A2 )=25(0.4)+15(0.4)-5(0.2)=15 EMV(A3)=15(0.4)+8(0.4)-0.5(0.2)=9.1
Best EMV (-one with maximum-) is EMV(A2 ). Thus choose A2 i.e build new facility

Question The manufacturer of summering pools must determine in advance of the summer season the
number of pools that must be produced for the coming year. Each summering pool costs $ 500 and sells at
$1000. Any summering pool that is unsold at the end of the season may be disposed off at $300 each. In
order to decide the number of pools to produce, the manufacturer must obtain information pertaining to the
demand for the summering pool. Based on past experience, the following levels of demand are postulated
(assumed). (i) Low demand = 1 000 pods demanded (ii) Moderate demand = 5 000 pods demanded
(iii) High demand = 10 000 pods demanded. If the probabilities of low, moderate & high demand are 0.2,
0.5 and 0.3 respectively. Prepare the gains pay-off table hence determine the best course of action using
both maximum likelihood and the ENV criterions.

Example 11 A Company is considering purchasing a new machine that is expected to save a considerable
amount of operational cost associated with the current machine. The new machine costs $10 000 and is
expected to save half a dollar per hour over the current. There is a considerable amount of uncertainty
concerning the expected number of hours that the company will actually use the new machine. The
management of the company has expected the uncertainty in the basis of the following probability
distribution. Should the company buy the machine?

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 14
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

No of hours 10,000 20,000 30,000 40,000

Probability 0.1 0.3 0.5 0.1
Solution:
Let X be the no. of hrs of use of the new machine serves and Let S be the savings due to the new machine.
Thus, S = 0.5x − 10 000 ⇒ E(S) = 0.5 E(X) – 10 000
But E(X) = 0.1(10 000) + 0.3(20 000) + 0.5(30 000)+0.1(40 000)=26 000
⇒ E(S) = 0.5(26 000)-10 000=$ 3 000
Conclusion: since E(S) is positive, the company should buy the machine.
Question: At a distance of 100 yards kibue hit target at an average of 60% of the time. In a local rifle
contest, each contestant will shoot on the target 3 times and receive the following rewards depending on the
number targets hit.
No of targets hit 3 2 1 0 Should Kibue enter the contest?
Reward $100 $50 $10 -$50

c) Expected Opportunity loss (EOL) Criterion

Payoffs and opportunity losses can be viewed as two sides of the same coin, depending on whether you
wish to view the problem in terms of maximizing expected monetary value or minimizing expected
opportunity loss.. Here we compute the expected regret for each course of action as follows;
EOL(𝐴𝑖 ) = ∑ 𝑅𝑖𝑗 𝑝(𝑆𝑗 )
Where Rij is the regret or loss incurred by choosing action Ai and the state of nature Sj occurs or prevails
over the other states of nature. The decision criterion is to select the course of action with the smallest EOL.
Selecting the course of action with the smallest EOL is equivalent to selecting the course of action with the
largest EMV ie Choose action Ai with Min{EOL(𝐴𝑖 )}
𝐴𝑖

Example 12 Consider the following pay-off table and obtain the best course of action using the Expected
Opportunity loss (EOL) criterion
state of Nature
Actions S1 S2 S3
A 60 100 120
B 90 60 110
C 80 110 90
Prob 0.5 0.3 0.2
Solution
Regret matrix::- Since we have profit state of Nature
R ij = Max Vij – Vij see regret table alongside Actions S1 S2 S3
𝑆𝑗
EOL (A) =30(0.5) + 10(0.3) +0(0.2) = 18 A 30 10 0
EOL (B) =0(0.5) + 50(0.3) +10(0.2) = 17 B 0 50 10
EOL (C) =10(0.5) + 0(0.3) +30(0.2) = 11 C 10 0 30
This is the best EOL thus C is the optimal course of ction. Prob 0.5 0.3 0.2

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 15
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

Question Consider the following pay-off table and obtain the best course of action using EOl criterion
a) Demand c) state of Nature
Alternatives High Moderate Low Actions S1 S2 S3 S4
A 80 110 120 A 70 100 100 130
B 120 70 110 B 220 50 90 120
C 80 120 90 C 90 80 80 100
Probability 0.2 0.5 0.3 Prob 0.32 0.25 0.28 0.15

state of Nature d) state of Nature

b) Actions S1 S2 S3 Actions S1 S2 S3
A 60 110 120
A 10 10 10
B 110 60 110
B 7 12 12
C 80 90 100
C 4 2 16
D 80 100 110
Prob 0.3 0.5 0.2
Prob 0.25 0.45 0.3

Decision Tree with Probabilities

Decisions that can be analyzed using pay off table can be display in a decision tree. We will therefore
analyze some decisions using decision trees. Although a Payoff Table (Decision Table) is convenient in
problems having one set of decisions and one set of states of nature, many problems include sequential
decisions and states of nature. When there are two or more sequential decisions, and later decisions are
based on the outcome of prior ones, the decision tree approach becomes appropriate. A decision tree is a
graphic display of the decision process that indicates decision alternatives, states of nature and their
respective probabilities, and payoffs for each combination of decision alternative and state of nature.

We could also use the decision tree approach outlined here instead of the payoffs table approach. First,
draw a decision tree to describe the sequential nature of the problem. If we use the EMV criterion, the next
step is to determine the probabilities for each of the states of nature and compute the expected value at each
chance node. Then select the decision branch leading to the chance node with the best expected value. The
decision alternative associated with this branch is the recommended decision.

Example 13 PDC is optimistic about the potential for the luxury high-rise condominium complex.

Suppose that this optimism leads to an initial subjective probability assessment of 0.8 that

demand will be strong (s1) and a corresponding probability of 0.2 that demand will be weak (s2).

Using a decision tree find the optimal course of action.

Solution
Figure 3 on page 17 below shows the decision tree for the PDC Construction Company

We compute the expected value for each of the three decision alternatives as follows

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 16
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

EMV (Node 2) =8(0.8) + 7(0.2) = 7.8 EMV (Node 3) =14(0.8) + 5(0.2) = 12.2
EMV (Node 4) =20(0.8) +-9(0.2) = 14.2 optimal value for node 1 is $14.2 miliions
Thus, the recommended decision is to make a large condominium complex, with an EMV of $14.2 million.
Figure 3 A Decision Tree for the PDC Construction Company he

Expected Value of Perfect Information (EVPI)

In most cases the decision maker does not know the state of Nature with certainty. EVPI also called the cost
of uncertainty is the expected opportunity loss associated with the optimal decision. It is actually the
maximum amount that the decision maker is willing to pay in order to know precisely the states of nature
that will be in effect. It also represents the difference between expected profit under certainty (EVUC) and
the EMV of the best alternative.
Example 14 Obtain the Expected Value of Perfect Information (EVPI) for the pay-off table in example 10
Solution
Best EMV (-one with maximum-) is EMV(A2 )=15. EVUC=25(0.4)+15(0.4)-0.5(0.2)=15.9
Therefore EVPI= EVUC- Best EMV =$0.9

d) Return-to-Risk Ratio
Unfortunately, neither the expected monetary value nor the expected opportunity loss criterion takes into
account the variability of the payoffs for the alternative courses of action under different states. Example 11
illustrates the return-to-risk ratio (RTRR) criterion.

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 17
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

Example 15 The manager of Reliable Fund has to decide between two stocks to purchase for a short-term
investment of one year. An economist at the company has predicted returns for the two stocks under four
economic conditions: recession, stability, moderate growth, and boom. The table below presents the
predicted one-year return of a $1,000 investment in each stock under each economic condition.
Economic Condition EMV
Stock Recession Stability Moderate Growth Boom
A 30 70 100 150 91
B -50 30 250 400 162
Probability 0.1 0.4 0.3 0.2
From the above table, you see that the return for stock A varies from $30 in a recession to $150 in an
economic boom, whereas the return for stock B (the one chosen according to the expected monetary value
and expected opportunity loss criteria) varies from a loss of $50 in a recession to a profit of $400 in an
economic boom.
To take into account the variability of the states of nature (in this case, the different economic conditions),
we can compute the variance and standard deviation of each stock, Using the information presented in
above table for stock A 𝐸𝑀𝑉(𝐴) = 𝜇𝐴 = $91 and the variance is
m
 A2   (Vij  A )2  P( S j )  0.1(61)2  0.4(21)2  0.3(9)2  0.2(59)2  1,269   A  $35.62. For stock
j 1

A 𝐸𝑀𝑉(𝐵) = 𝜇𝐵 = $162 and the variance is

m
 B2   (Vij  B )2  P( S j )  0.1(212)2  0.4(132)2  0.3(88)2  0.2(238)2  25,116   B  $158.48.
i
j 1
m
Remark: Notice that 𝐸𝑀𝑉(𝐴) = 𝜇𝐴   Vij  P( S j ) and the variance is
j 1
m m
 2  E (Vij  A )2   (Vij  A ) 2  P( S j )
Ai i i
or  2  E (V 2 )   2  V 2  P( S j )   2
Ai ij Ai ij Ai
j 1 j 1

Because you are comparing two stocks with different means, you should evaluate the relative risk
associated with each stock. Once you compute the standard deviation of the return from each stock, you
compute the coefficient of variation discussed in STA 2100 Substituting 𝜎 for S and EMV for 𝑥̅ in the
  Ai 
formular for the coefficient of variation we get CV(A i ) =    100%
 EMv(Ai ) 
 35.62   158.48 
CV(A) =    100%  39.1% and CV(B) =    100%  97.8%
 91   162 
Thus, there is much more variation in the return for stock B than for stock A.
When there are large differences in the amount of variability in the different events, a criterion other than
EMV or EOL is needed to express the relationship between the return (as expressed by the EMV) and the
risk (as expressed by the standard deviation). The following equation defines the return-to-risk ratio
(RTRR) as the expected monetary value of action Ai divided by the standard deviation of action Ai.
EMv(Ai )
RTRR(Ai ) =
 Ai
Criterion: Select the course of action with the largest RTRR.
For each of the two stocks discussed above, compute the return-to-risk ratio as follows.
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 18
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

For stock A and B, the return-to-risk ratio are given by

91 162
RTRR(A) =  2.55 and RTRR(B) =  1.02
35.62 158.48
Thus, relative to the risk as expressed by the standard deviation, the expected return is much higher for
stock A than for stock B. Stock A has a smaller expected monetary value than stock B but also has a much
smaller risk than stock B. The return-to-risk ratio shows A to be preferable to B.

Exercise 3
1. For the following payoff table, the probability of event S1 is 0.8, the probability of event S2 is 0.1, and the
probability of event S3 is 0.1:
Event a) Determine the optimal action using the EM), the
(EOL) and the return to risk ratio criterions
Actions S1 S2 S3
b) Explain the meaning of EVPI in this problem..
A 50 300 500
B 10 100 200
2. Consider the following costs payoff table. Using the EMV, the (EOL) and the return to risk ratio criterion find
the optimal action
State of Nature 3. Refer to question 4 in exercise 2. If the
Actions S1 S2 S3 probabilities of cold weather (S1), warm weather
A 60 110 120 (S2), and rainy weather (S3) are 0.2, 0.4, and 0.4,
B 110 60 110 respectively, then what decision should be made
C 80 90 100 using the EMV, the EOL and the return to risk
D 80 100 110 ratio criterion? What is the EVPI for this situation?
Probability 0.25 0.45 0.30
4. Refer to question 5 in exercise 2. If the probabilities of each economic condition are 0.5, 0.1, 0.35, and 0.05
respectively, what investment would be made using the EMV, the (EOL) and the return to risk ratio
criterion? What is the EVPI for this situation?
5. Refer to question 7 in exercise 2. If the probability of brisk business is .40 and for slow business is .60, find
the expected value of perfect information.
6. If the local operations manager in question 8 exercises 2 thinks the chances of low, medium, and high
compliance are 20%, 30%, and 50% respectively, what are the expected net revenues for the number of
workers he will decide to hire?
7. An entrepreneur must decide how many tones of plastic shipping pallets to produce each week for sale. His
manufacturing manager has determine with an accounts assistance that the total cost per tone to produce
pallets is $25. There is also an additional cost of $2 per tone of pallets sold to shippers. The pallets are sold
for $50 per tone> pallets not sold at the end of the week are disposed off to a local farmer who will pay $5
per tonne. It’s assumed that the weekly demand for of plastic shipping pallets will range from 0 to 5 tonnes.
Construct the manufacturers profit pay-off table. If after consultation with an experienced market analyst
entrepreneur assesses the accompanying probability distribution to weekly demand to shippers of plastic
pallets as;
Demand 0 1 2 3 4 5
Probability 0.05 0.1 0.25 0.4 0.15 0.05
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 19
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

Determine the number of tones to produce if the entrepreneur wishes to maximize expected profit. What is
the entrepreneur Expected Value of Perfect Information (EVPI)? In simple language explain the meaning of
EVPI to the entrepreneur.
8. Inflation tends to boast interest rates of loans of all types. As a partial hedge against inflation, some lending
institutions offer variable rates loans to borrowers with high credit ratings. The borrower can then accept
either a fixed rate loan with certain interest obligations or a variable rate loan that may result in either
interest savings or additional interest costs to the borrower depending on the future state if the economy.
Suppose an individual wishes to borrow $ 10,000 for 1 year when the prevailing interest rate is 9%. After
consulting an economist, the individual attributes the probability distribution for the prevailing lending
rates over the next 1 year to be;
Interest Rate 8% 8.50% 8% 9.50% 10%
Probability 0.1 0.25 0.5 0.1 0.05
The borrower must decide whether to accept the prevailing interest rate of 9% or undertake a variable rate,
a) Construct an opportunity loss table for the c) How much would the borrower be willing to
borrower pay to know exactly the interest rate that would
b) If the borrower wishes to minimize the be in effect at the end of the year?
expected opportunity loss, which type of loan
should he undertake?
9. For a potential investment of $1,000, if a stock has an EMV of $100 and a standard deviation of $25, what
is the return-to-risk ratio?
10. A stock has the following predicted returns under the following economic conditions:
Economic Compute the
Condition Probability Return ($) a) expected monetary value.
Recession 0.3 50 b) standard deviation.
Stable Economy 0.3 100 c) coefficient of variation.
Moderate Growth 0.3 120 d) return-to-risk ratio
Boom 0.1 200
11. The following are the returns ($) for two stocks: Which stock would you choose and why?
A B A B
Expected Monetary value 90 60 Expected Monetary value 60 60
Standard Deviation 10 10 Standard Deviation 20 10
12. A vendor at a local baseball stadium must Weather
determine whether to sell ice cream or soft drinks Actions Cool Warm
at today’s game. She believes that the profit made Sell Soft Drinks 50 60
will depend on the weather. The payoff table (in $) Sell Ice Cream 30 90
is as shown.
a) Based on her past experience at this time of year, the vendor estimates the probability of warm weather
as 0.60.
b) Determine the optimal action based the EMV, EOL and the return to risk ratio criterions.
c) Explain the meaning of the expected value of perfect information (EVPI) in this problem.
13. The Islander Fishing Company purchases clams for $1.50 per pound from fishermen and sells them to
various restaurants for $2.50 per pound. Any clams not sold to the restaurants by the end of the week can be
Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 20
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

sold to a local soup company for $0.50 per pound. The company can purchase 500, 1,000, or 2,000 pounds.
The probabilities of various levels of demand are as follows:
Demand (Pounds) 500 1,000 2,000
Probability 0.2 0.4 0.4
a) For each possible purchase level (500, 1,000, or 2,000 pounds), compute the profit (or loss) for each
level of demand.
b) Determine the optimal action based the EMV, EOL and the return to risk ratio criterions.
c) Explain the meaning of the expected value of perfect information (EVPI) in this problem
d) Suppose that clams can be sold to restaurants for $3 per pound. Repeat (a) with this selling price for
clams and compare the results with those in a
e) What would be the effect on the results in (a) if the probability of the demand for 500, 1,000, and 2,000
clams were 0.4, 0.4, and 0.2, respectively?.
14. An investor has a certain amount of money available to invest now. Three alternative investments are
available. The estimated profits ($) of each investment under each economic condition are indicated in the
following payoff table Based on his own past experience, the investor assigns the following probabilities to
each economic condition:
State of the Economy
Actions Economy declines No Change Economy expands
A $1,500 $1,000 $2,000
B -$2,000 $2,000 $5,000
C -$7,000 -$1,000 $20,000
Prior prob 0.3 0.5 0.2
a) Based on her past experience at this time of year, the vendor estimates the probability of warm weather
as 0.60.
b) Determine the optimal action based the EMV, EOL and the return to risk ratio criterions.
c) Explain the meaning of the expected value of perfect information (EVPI) in this problem.
15. Consider the payoff table you developed on building a small factory or a large factory for manufacturing
designer jeans. Given the results of that problem, suppose that the probabilities of the demand are as
follows:
Demand 10,000 20,000 50,000 100,000
Probability 0.1 0.4 0.2 0.3
a) Compute the expected monetary value (EMV) and the expected opportunity loss (EOL for building a
small factory and building a large factory.
b) Explain the meaning of the expected value of perfect information (EVPI) in this problem.
c) Based on the results of a) would you choose to build a small factory or a large factory? Why?
d) Compute the coefficient of variation for building a small factory and a large factory.
e) Compute the return-to-risk ratio (RTRR) for building a small factory and building a large factory.
f) Based on (d) and (e), would you choose to build a small factory or a large factory? Why?
g) Compare the results of (f) and (c) and explain any differences.
h) Suppose that the probabilities of demand are 0.4, 0.2, 0.2, and 0.2, respectively. Repeat (a) through (g)
with these probabilities and compare the results with those in (a)–(g).

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 21
 May the key to your success rest not in your professional skills or personal charisma; rather, may the dynamic of your strength lay in the presence and power of God.
Time is precious, but we do not know yet how precious it really is. We will only know wh

16. Consider the payoff table you developed to assist an author in choosing between signing with company A
or with company B. Given the results computed in that problem, suppose that the probabilities of the levels
of demand for the novel are as follows:
Demand 1,000 2,000 5,000 10,000 50,000
Probability 0.45 0.20 0.15 0.10 0.10
a) Compute the expected monetary value (EMV) and the expected opportunity loss (EOL for signing with
company A and with company B.
b) Explain the meaning of the expected value of perfect information (EVPI) in this problem.
c) Based on the results of a) would you choose to sign with company A or company B? why?
d) Compute the coefficient of variation for signing with company A and with company B.
e) Compute the return-to-risk ratio for signing with company A and with company B.
f) Based on (d) &(e), would you choose to sign with company A or with company B? Why?
g) Compare the results of (f) and (c) and explain any differences.
h) Suppose that the probabilities of demand are 0.3, 0.2, 0.2, 0.1, and 0.2 respectively. Repeat (a) -(g) with
these probabilities and compare the results with those in (a)–(g).
17. Consider the payoff table you developed to determine whether to purchase 100, 200, 500, or 1,000
Christmas trees. Given the results of that problem, suppose that the probabilities of the demand for the
different number of trees are as follows:
Demand 100 200 500 1,000
Probability 0.2 0.5 0.2 0.1
a) Compute the expected monetary value (EMV) and the expected opportunity loss (EOL for purchasing
100, 200, 500, and 1,000 trees
b) Explain the meaning of the expected value of perfect information (EVPI) in this problem.
c) Based on the results of part a) would you choose to purchase 100, 200, 500, and 1,000 trees? Why?
d) Compute the coefficient of variation for purchasing 100, 200, 500, and 1,000 trees
e) Compute the return-to-risk ratio (RTRR) for purchasing 100, 200, 500, and 1,000 trees
f) Based on (d) and (e), would you choose to purchase 100, 200, 500, and 1,000 trees? Why?
g) Compare the results of (f) and (c) and explain any differences.
h) Suppose that the probabilities of demand are 0.4, 0.2, 0.2,and 0.2 respectively. Repeat (a) through (g)
with these probabilities and compare the results with those in (a)–(g).
18. An oil company has some land that is reported to possibly contain oil. The company classifies such land
into four categories by the total number of barrels that are expected to be obtained from the well, i.e. a
500,000 – barrel well, 200,000 – barrel well, 50,000 – barrel well, and a dry well. The company is faced
with deciding whether to drill for oil, to unconditionally lease the land or to conditionally lease the land at a
rate depending upon oil strike. The cost of drilling the well is $100,000; if it is a producing well and the
cost of drilling is $75,000 if it is a dry well. For producing well, the profit per barrel of oil is $1.50, ( after
deduction of processing and all other costs except drilling costs). Under the unconditional lease agreement,
the company receives $45,000 for the land whereas for the conditional lease agreement the company
receives 50 cents for each barrel of oil extracted if it is a 500,000 or 200,000 barrel oil strike and nothing if
otherwise. The probability for striking a 500,000– barrel well is 0.1, probability for striking a 200,000 –
barrel well is 0.15, probability for striking a50 000– barrel well is 0.25, and probability for a dry well is 0.5.
a) Make a profit payoff table for the oil company
b) Find the optimal act according to Expected opportunity loss criteria

Time is precious, but we do not know yet how precious it really is. We will only know when we are no longer able to take advantage of it Page 22