An Introduction to Decision

Theory
Session 4

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Statistical Decision Theory
 Statistical decision theory is concerned with making
decisions from a set of alternatives
Examples
 Ford Motor Company must decide whether to purchase
assembled door locks for the 2017 F-150 or to
manufacture the locks themselves
 If sales increase – it’s more profitable to make
 If sales level off or decline – it’s more profitable to buy
 GE is considering three options regarding the prices of
their refrigerators next year, raise the prices 5%, 2.5%,
or leave the prices as they are
 The decision will be based on sales estimates and
what the other refrigerator producers might do

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Elements of a Decision
 The choices available
 The various courses of action are called the acts
or alternatives
 The states of nature
 The uncontrollable future events are called the
states of nature
 The payoffs
 The consequence of a particular decision
alternative and state of nature is the payoff
 We can make better decisions if we establish
probabilities for the states of nature

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Decision Making under Uncertainty

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Payoff Table

Bob Hill, a small investor, has $1,100 to invest. He has studied

several common stocks and narrowed his choices to three: Kayser
Chemicals, Rim Homes, and Texas Electronics. He estimates that if
stock prices increase drastically (a bull market), his investment in
Kayser stock would more than double. However, if
stock prices decrease (a bear market), the value of the Kayser
stock could drop to $1000. His predictions for the three stocks are
shown in the Payoff Table below.

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Expected Payoff

In the expected
monetary value
(EMV) criterion,
the expected
value for each
decision
alternative is
computed, and the
Copyright ©2021 McGraw-Hill Education. All optimal oneNoisreproduction or
rights reserved.
distribution without the prior written consent of McGraw-Hill Education.
Opportunity Loss
 The difference between the optimal decision and
any other decision is the opportunity loss or regret
due to making a decision other than the optimum
 An opportunity loss table can be developed
 An opportunity loss table is constructed by taking
the difference between the optimal decision for each
state of nature and the other decision alternatives
 The expected opportunity loss (EOL) is similar to the
expected monetary value (EMV)
 The opportunity loss is combined with the
probabilities of the various states of nature for each
decision alternative to determine the expected
opportunity loss
Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or
distribution without the prior written consent of McGraw-Hill Education.
Opportunity Loss Table
Suppose Bob Hill had purchased Rim Homes stock and then a bull
market developed. The value of the Rim Homes stock did increase
from $1,100 to $2,200 as expected. But had Bob bought Kayser
Chemicals stock and market values increased, the value of his stock
purchase would be $2,400; so he missed making an extra $200. The
$200 is the opportunity loss for not knowing the future state of the
market.

Notice, that Kayser Chemicals stock would be a good investment

choice in a rising (bull) market, Texas Electronics stock would be the
best buy in a declining (bear) market, and Rim Homes stock is a
compromise.
Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or
distribution without the prior written consent of McGraw-Hill Education.
Expected Opportunity Loss

The two approaches,

lowest expected
opportunity loss and
highest expected payoff,
will always lead to the
same decision.
Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or
distribution without the prior written consent of McGraw-Hill Education.
Value of Perfect Information
VALUE OF PERFECT INFORMATION The difference
between the maximum expected payoff under conditions
of certainty and the maximum expected payoff under
uncertainty.

If Bob knew precisely what the market would do, he could

maximize profit by always buying the correct stock. What if
someone could supply him with information about when the
market will rise or decline? What would this information be
worth?

EVPI = Expected value under certainty − Expected value

under uncertainty
= $1,900 − $1,840
Copyright = $60 Education. All rights reserved. No reproduction or
©2021 McGraw-Hill
distribution without the prior written consent of McGraw-Hill Education.
Sensitivity Analysis
 Sensitivity analysis examines the effects of
various probabilities for the states of nature
on the expected values
 The rankings of the decision alternatives are
frequently not highly sensitive to changes
within a plausible range

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Question 1 LO20-
2
The following payoff table was developed. Let
P(S1) = .30, P(S2) = .50, and P(S3) = .20.
Compute the expected monetary value for each
of the alternatives. What decision would you
recommend?

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Question 9 LO20-
6
Refer to Exercise 1. Revise the probabilities as
follows: P(S1) = .50, P(S2) = .20, and P(S3)
= .30 and use Expected Monetary Value to
evaluate the decision. Does this change the
decision?

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Decision Making with Uncertainty:
Using the Decision Trees

Some of Slides has been taken from the book of Quantitative

© 2006 by Prentice Hall, Inc.
Analysis For Management by Render et al., 11 ed);
Upper Saddle River, NJ 07458

 Decision trees are most beneficial when a

sequence of decisions must be made.
 All information included in a payoff table is
also included in a decision tree.

© 2006 by Prentice Hall, Inc. 3-14

Upper Saddle River, NJ 07458
 Five Steps to Decision Tree Analysis
1. Define the problem.
2. Structure or draw the decision
tree.
3. Assign probabilities to the states
of nature.
4. Estimate payoffs for each
possible combination of
alternatives and states of nature.
5. Solve the problem by computing
expected monetary values
(EMVs) at each state of nature
node.
© 2006 by Prentice Hall, Inc. 3-15
Upper Saddle River, NJ 07458
Structure of Decision Trees

A graphical representation where:

A decision node (indicated by a

square ) from which one of
several alternatives may be
chosen.

A state-of-nature node (indicated

by a circle ) out of which one
state of nature will occur.

© 2006 by Prentice Hall, Inc. 3-16

Upper Saddle River, NJ 07458
Example of Decision Tree Graph
Example
Joe’s garage is considering hiring another mechanic. The
mechanic would cost them an additional $50,000 /
year in salary and benefits.
 If there are a lot of accidents in Iowa City this year,
they anticipate making an additional $70,000 in net
revenue.
 If there are not a lot of accidents, they could lose
$20,000 off of last year’s total net revenues.
 Because of all the ice on the roads, Joe thinks that
there will be a 70% chance of “a lot of accidents” and
a 30% chance of “fewer accidents”.
 Assume if he doesn’t expand, he will have the same
revenue as last year. Source: (INSOF, International
School of Engineering)
20-18 .
Continued…

Estimated value of “Hire Mechanic” =

NPV =.7(70,000) + .3(- $20,000) - $50,000 =
- $7,000
Therefore, you should not hire the mechanic
.
Example
Bob Hill, a small investor, has $1,100 to invest. He has studied
several common stocks and narrowed his choices to three: Kayser
Chemicals, Rim Homes, and Texas Electronics. He estimates that if
stock prices increase drastically (a bull market), his investment in
Kayser stock would more than double. However, if
stock prices decrease (a bear market), the value of the Kayser
stock could drop to $1000. His predictions for the three stocks are
shown in the Payoff Table below.

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
Decision Trees
 Decision trees are useful for structuring the
various alternatives
 They present a picture of the various courses
of action and the possible states of nature

Copyright ©2021 McGraw-Hill Education. All rights reserved. No reproduction or

distribution without the prior written consent of McGraw-Hill Education.
 Thompson Lumber:
Payoff Table

State of Nature
Alternativ Unfavora
Favorabl
e ble
e Market
Market
($)
($)
Construct
a large 200,000 -180,000
plant
Construct
a small 100,000 -20,000
plant
Do
0 0
nothing
Probabiliti
0.50 0.50
es
© 2006 by Prentice Hall, Inc. 3-22
Upper Saddle River, NJ 07458
 John Thompson’s Backyard Storage
Sheds
Define problem To manufacture or market backyard
storage sheds

List alternatives 1. Construct a large new plant

2. A small plant
3. No plant at all

Identify outcomes The market could be favorable or

unfavorable for storage sheds

List payoffs List the payoff for each state of

nature/decision alternative
combination
Select a model Decision tables and/or trees can be
used to solve the problem

Apply model and Solutions can be obtained and a

make decision sensitivity analysis used to make a
decision

© 2006 by Prentice Hall, Inc. 3-23

Upper Saddle River, NJ 07458
Thompson’s Decision Tree
Step 1: Define the problem
Let's re-look at John Thompson’s decision
regarding storage sheds. This simple
problem can be depicted using a
decision tree.

Step 2: Draw the tree

A State Favorable Market
of
Nature
Node ct 1
r u
o n st e Unfavorable Market
C arg
L la nt
A P
Decisi Favorable Market
on Construc
t Small
Node Plant 2
Do Unfavorable Market
No
th in g

© 2006 by Prentice Hall, Inc. 3-24

Upper Saddle River, NJ 07458
Thompson’s Decision Tree
Step 3: Assign probabilities to
the states of nature.
Step 4: Estimate payoffs.
A State of
Nature Node
Favorable (0.5)$200,000
Market

t 1
t ruc
o ns e -$180,000
Unfavorable (0.5)
C arg Market
L la nt
A P
Decision
Favorable (0.5)$100,000
Node Construc Market
t Small
Plant 2
Do Unfavorable (0.5)-$20,000
No Market
th in g

0
© 2006 by Prentice Hall, Inc. 3-25
Upper Saddle River, NJ 07458
Thompson’s Decision Tree
Step 5: Compute EMVs and
make decision.
A State of
Nature
Node Favorable (0.5)$200,000
Market

1
u ct ntEMV
r
o nst e Pla =$10,000 Unfavorable
Market
(0.5)
-$180,000
C arg
L
A Decision
Node Favorable (0.5)
Construct Market $100,000
Small
Plant
2
EMV
Do =$40,000 Unfavorable (0.5)
-$20,000
No Market
th in g

© 2006 by Prentice Hall, Inc. 3-26

Upper Saddle River, NJ 07458
Practice
Leo can purchase a historic home for $200,000 or land in a growing
area for $50,000. There is a 60% chance the economy will grow and
a 40% chance it will not. If it grows, the historic home will appreciate
in value by 15% yielding a $30,000 profit. If it does not grow, the
profit is only $10,000.
If Leo purchases the land, he will hold it for 1 year to assess the
economic growth. If the economy grew during the first year, there is
an 80% chance it will continue to grow. If it did not grow during the
first year, there is a 30% chance it will grow in the next 4 years.
After a year, if the economy grew, Leo would decide either to build
and sell a house or simply sell the land. It will cost Leo $75,000 to
build a house that will sell for a profit of $55,000 if the economy
grows, or $15,000 if it does not grow.
Leo can sell the land for a profit of $15,000.
If, after a year, the economy does not grow, Leo will either develop
the land, which will cost $75,000, or sell the land for a profit of
$5,000.
Upper Saddle River, If he develops the land and the economy
© 2006 by Prentice Hall, Inc.
NJ 07458
3-27 begins to grow, he

will make $45,000. If he develops the land and the economy does