Unit 3

Decision Analysis Model

Nguyen Tai Vuong

School of Economics and Management
HUST

Learning Objectives
After completing this unit, students will be able to:

1. List the steps of the decision-making process.

2. Describe the types of decision-making environments.
3. Make decisions under uncertainty.
4. Use probability values to make decisions under risk.
5. Develop accurate and useful decision trees.
6. Revise probabilities using Bayesian analysis.
7. Use computers to solve basic decision-making problems.
8. Understand the importance and use of utility theory in decision
making.

Decision Analysis 3-2

1
 Unit Outline

3.1 Introduction
3.2 The Six Steps in Decision Making
3.3 Types of Decision-Making Environments
3.4 Decision Making under Uncertainty
3.5 Decision Making under Risk
3.6 Decision Trees
3.7 How Probability Values Are Estimated by Bayesian Analysis
3.8 Utility Theory

Decision Analysis 3-3

3.1 Introduction

 What is involved in making a good decision?

 Decision theory is an analytic and systematic approach to

the study of decision making.

 A good decision is one that is based on logic, considers

all available data and possible alternatives, and the
quantitative approach described here.

Decision Analysis 3-4

2
 3.2 The Six Steps in Decision Making

1. Clearly define the problem at hand.

2. List the possible alternatives.
3. Identify the possible outcomes or states of nature.
4. List the payoff (typically profit) of each combination of
alternatives and outcomes.
5. Select one of the mathematical decision theory models.
6. Apply the model and make your decision.

Decision Analysis 3-5

Thompson Lumber Company

Step 1 – Define the problem.
 The company is considering expanding by manufacturing
and marketing a new product – backyard storage sheds.
Step 2 – List alternatives.
 Construct a large new plant.
 Construct a small new plant.
 Do not develop the new product line at all.
Step 3 – Identify possible outcomes.
 The market could be favorable or
unfavorable.

Decision Analysis 3-6

3
 Thompson Lumber Company
Step 4 – List the payoffs.
 Identify conditional values for the profits for large plant,
small plant, and no development for the two possible
market conditions.
Step 5 – Select the decision model.
 This depends on the environment and amount of risk and
uncertainty.
Step 6 – Apply the model to the data.
 Solution and analysis are then used to aid in decision-
making.

Decision Analysis 3-7

Thompson Lumber Company

Decision Table with Conditional Values for
Thompson Lumber
STATE OF NATURE

FAVORABLE UNFAVORABLE
ALTERNATIVE MARKET ($) MARKET ($)
Construct a large plant 200,000 –180,000

Construct a small plant 100,000 –20,000

Do nothing 0 0

Decision Analysis 3-8

4
 3.3 Types of Decision-Making Environments

Type 1: Decision making under certainty

 The decision maker knows with certainty the consequences
of every alternative or decision choice.

Type 2: Decision making under uncertainty

 The decision maker does not know the probabilities of the
various outcomes.

Type 3: Decision making under risk

 The decision maker knows the probabilities of the various
outcomes.

Decision Analysis 3-9

3.4 Decision Making Under Uncertainty

There are several criteria for making decisions under uncertainty:

1. Maximax (optimistic)
Phương án có giá trị lớn nhất trong các trạng thái đem lại kết quả lớn nhất (Lạc quan)
2. Maximin (pessimistic)
Phương án có giá trị nhỏ nhất trong các trạng thái đem lại kết quả lớn nhất (Bi quan)
3. Criterion of realism (Hurwicz)
Tiêu chuẩn hiện thực (Hurwcz)
4. Equally likely (Laplace)
Tiêu chuẩn đồng đều ngẫu nhiên (Laplace)
5. Minimax regret
Phương án có giá trị nhỏ nhất trong các trạng thái có giá trị lớn nhất bị bỏ lỡ
Decision Analysis 3-10

5
 Maximax Model

Used to find the alternative that maximizes the maximum

payoff.
 Locate the maximum payoff for each alternative.
 Select the alternative with the maximum number.

𝑴𝒂𝒙 𝑴𝒂𝒙 𝑷𝒊𝒋

𝒊 𝒋

Decision Analysis 3-11

Maximax model

STATE OF NATURE
FAVORABLE UNFAVORABLE MAXIMUM IN
ALTERNATIVE MARKET ($) MARKET ($) A ROW ($)

Construct a large plant 200,000 –180,000 200,000

Maximax
Construct a small
100,000 –20,000 100,000
plant
Do nothing 0 0 0

Decision Analysis 3-12

6
 Maximin Model

Used to find the alternative that maximizes the minimum

payoff.
 Locate the minimum payoff for each alternative.
 Select the alternative with the maximum number.

𝑴𝒂𝒙 𝑴𝒊𝒏 𝑷𝒊𝒋

𝒊 𝒋

Decision Analysis 3-13

Maximin Model

STATE OF NATURE
FAVORABLE UNFAVORABLE MINIMUM IN
ALTERNATIVE MARKET ($) MARKET ($) A ROW ($)

Construct a large plant 200,000 –180,000 –180,000

Construct a small
100,000 –20,000 –20,000
plant
Do nothing 0 0 0
Maximin

Decision Analysis 3-14

7
 Criterion of Realism (Hurwicz)
This is a weighted average compromise between optimism
and pessimism.
 Select a coefficient of realism , with 0 ≤ α ≤ 1.
 A value of 1 is perfectly optimistic, while a value of 0 is perfectly
pessimistic.
 Compute the weighted averages for each alternative:

𝑴𝒂𝒙 𝑷𝒊𝒋 𝑴𝒊𝒏 𝑷𝒊𝒋

𝑾𝒊 =∝ + (𝟏 − 𝜶)
𝒋 𝒋

 Select the alternative with the highest value:

𝑴𝒂𝒙(𝑾𝒊 )

Decision Analysis 3-15

Criterion of Realism (Hurwicz)

 For the large plant alternative using  = 0.8:
(0.8)(200,000) + (1 – 0.8)(–180,000) = 124,000
 For the small plant alternative using  = 0.8:
(0.8)(100,000) + (1 – 0.8)(–20,000) = 76,000
STATE OF NATURE
CRITERION
FAVORABLE UNFAVORABLE OF REALISM
ALTERNATIVE MARKET ($) MARKET ($) ( = 0.8) $

Construct a large plant 200,000 –180,000 124,000

Realism
Construct a small
100,000 –20,000 76,000
plant
Do nothing 0 0 0

Decision Analysis 3-16

8
 Equally Likely (Laplace)

Considers all the payoffs for each alternative

 Find the average payoff for each alternative.

∑𝒏𝒋 𝟏 𝑷𝒊𝒋
𝑨𝒊 =
𝑵𝒖𝒎𝒃𝒆𝒓 𝒐𝒇 𝒐𝒖𝒕𝒄𝒐𝒎𝒆𝒔 𝒐𝒓 𝒔𝒕𝒂𝒕𝒆 𝒐𝒇 𝒏𝒂𝒕𝒖𝒓𝒆

 Select the alternative with the highest average.

𝑴𝒂𝒙(𝑨𝒊 )

Decision Analysis 3-17

Equally Likely (Laplace)

STATE OF NATURE
FAVORABLE UNFAVORABLE ROW
ALTERNATIVE
MARKET ($) MARKET ($) AVERAGE ($)

Construct a large plant 200,000 –180,000 10,000

Construct a small
100,000 –20,000 40,000
plant
Equally likely
Do nothing 0 0 0

Decision Analysis 3-18

9
 Minimax Regret
Based on opportunity loss or regret, this is the difference between the
optimal profit and actual payoff for a decision.
1. Create an opportunity loss table by determining the opportunity
loss from not choosing the best alternative.
 Opportunity loss is calculated by subtracting each payoff in the column from
the best payoff in the column.

𝑴𝒂𝒙𝑷𝒊𝒋
𝑶𝑳𝒊𝒋 = ( ) − 𝑷𝒊𝒋
𝒊
2. Find the maximum opportunity loss for each alternative and pick
the alternative with the minimum number.
𝑴𝒊𝒏 𝑴𝒂𝒙 𝑶𝑳𝒊𝒋
𝒊 𝒋
Decision Analysis 3-19

Minimax Regret
Determining Opportunity Losses for Thompson Lumber

STATE OF NATURE

FAVORABLE MARKET ($) UNFAVORABLE MARKET ($)

200,000 – 200,000 0 – (–180,000)

200,000 – 100,000 0 – (–20,000)

200,000 – 0 0–0

Decision Analysis 3-20

10
 Minimax Regret
Opportunity Loss Table for Thompson Lumber

STATE OF NATURE

FAVORABLE UNFAVORABLE
ALTERNATIVE
MARKET ($) MARKET ($)

Construct a large plant 0 180,000

Construct a small plant 100,000 20,000

Do nothing 200,000 0

Decision Analysis 3-21

Minimax Regret

Thompson’s Minimax Decision Using Opportunity Loss

STATE OF NATURE
FAVORABLE UNFAVORABLE MAXIMUM IN
ALTERNATIVE
MARKET ($) MARKET ($) A ROW ($)

Construct a large plant 0 180,000 180,000

Construct a small
100,000 20,000 100,000
plant
Minimax
Do nothing 200,000 0 200,000

Decision Analysis 3-22

11
 Practice 1
Today’s Electronics specializes in manufacturing modern electronic components. It also builds
the equipment that produces the components. Phyllis Weinberger, who is responsible for
advising the president of Today’s Electronics on electronic manufacturing equipment, has
developed the following table concerning a proposed facility:

 Find suitable decision when applying different criteria for making decision under
uncertainty? (use alpha = 0.6 for strong market)
Decision Analysis 3-23

Practice 2
Hương has decided to lease battery for her electric car to save on gasoline expenses and to do
her part to help keep the environment clean. The car she selected is available from only one
dealer in the local area, but that dealer has several leasing options to accommodate a variety of
driving patterns. All the leases are for 1 year and require no money at the time of signing the
lease. The following table summarizes each of the three lease options:
Kilometer Cost per Excess
1-year lease Monthly Cost
Allowance Kilometer
Option 1 $330 24,000 $0.30
Option 2 $380 30,000 $0.25
Option 3 $430 36,000 $0.20

In evaluating these lease options, Hương would like to keep her costs as low as possible. As
experience, she does not drive more than 40,000 km per year.
(a) Develop a payoff (cost) table for this situation.
(b) What decision would Hương make if she were optimistic?
(c) What decision would Hương make if she were pessimistic?
Decision Analysis 3-24

12
 3.5 Decision Making Under Risk

 This is decision making when there are several possible states of

nature, and the probabilities associated with each possible state
are known.
 The most popular method is to choose the alternative with the
highest expected monetary value (EMV).

EMV (alternative i) = (payoff of first state of nature)

x (probability of first state of nature)
+ (payoff of second state of nature)
x (probability of second state of nature)
+ … + (payoff of last state of nature)
x (probability of last state of nature)

Decision Analysis 3-25

EMV Model
𝒎

𝑬𝑴𝑽(𝒊) = 𝑷(𝑺𝒋 ) × 𝑷𝒊𝒋

𝒋 𝟏

P(Sj): probability of state of nature j

Pij : payoff (profits or costs) of alternative i with state of nature j

 Chose an alternative that brings the largest EMV

 Note: Profits >< Costs payoff

Decision Analysis 3-26

13
 EMV for Thompson Lumber
 Suppose each market outcome has a probability of occurrence of 0.50.
 Which alternative would give the highest EMV?
 The calculations are:

Decision Analysis 3-27

EMV for Thompson Lumber

STATE OF NATURE
FAVORABLE UNFAVORABLE
ALTERNATIVE MARKET ($) MARKET ($) EMV ($)

Construct a large plant 200,000 –180,000 10,000

Construct a small
100,000 –20,000 40,000
plant
Do nothing 0 0 0
Probabilities 0.50 0.50

Largest EMV

Decision Analysis 3-28

14
 Expected Value of Perfect Information (EVPI)

 EVPI places an upper bound on what you should pay for additional
information.
EVPI = EVwPI – Maximum EMV

 EVwPI is the long run average return if we have perfect information

before a decision is made.

EVwPI = (best payoff for first state of nature) x (probability of first state of nature)
+ (best payoff for second state of nature) x (probability of second state of nature)
+…
+ (best payoff for last state of nature) x (probability of last state of nature)

Decision Analysis 3-29

EVPI Model
𝒎

𝑬𝑽𝒘𝑷𝑰 = 𝑷(𝑺𝒋 ) × max 𝑷𝒊𝒋

𝒊
𝒋 𝟏

𝑬𝑽𝑷𝑰 = 𝑬𝑽𝒘𝑷𝑰 − 𝑴𝒂𝒙(𝑬𝑴𝑽𝒊 )

EVPI: the added value when buying information (or maximum

value would pay for information)

Decision Analysis 3-30

15
 Expected Value of Perfect Information (EVPI)

 Suppose Scientific Marketing, Inc. offers analysis that

will provide certainty about market conditions (favorable).

 Additional information will cost $65,000.

 Should Thompson Lumber purchase the information?

Decision Analysis 3-31

Expected Value of Perfect

Information (EVPI)
Decision Table with Perfect Information

STATE OF NATURE
FAVORABLE UNFAVORABLE
ALTERNATIVE MARKET ($) MARKET ($) EMV ($)
Construct a large
200,000 -180,000 10,000
plant
Construct a small
100,000 -20,000 40,000
plant
Do nothing 0 0 0
Probabilities 0.5 0.5
With perfect
200,000 0 100,000
information

Decision Analysis
EVwPI 3-32

16
 Expected Value of Perfect
Information (EVPI)
The maximum EMV without additional information is $40,000.
EVPI = EVwPI – Maximum EMV
= $100,000 - $40,000
= $60,000

Decision Analysis 3-33

Expected Value of Perfect

Information (EVPI)
The maximum EMV without additional information is
$40,000.
EVPI = EVwPI – Maximum EMV
= $100,000 - $40,000
= $60,000

Decision Analysis 3-34

17
 Expected Opportunity Loss Model

 Expected opportunity loss (EOL) is the cost of not

picking the best solution.
 First construct an opportunity loss table.
 For each alternative, multiply the opportunity loss by the
probability of that loss for each possible outcome and add these
together.
 Minimum EOL will always result in the same decision as
maximum EMV.
 Minimum EOL will always equal EVPI.

Decision Analysis 3-35

EOL Model

𝑶𝑳𝒊𝒋 = 𝑴𝒂𝒙𝒊 (𝑷𝒊𝒋 ) − 𝑷𝒊𝒋

𝒎

𝑬𝑶𝑳(𝒊) = 𝑷(𝑺𝒋 ) × 𝑶𝑳𝒊𝒋

𝒋 𝟏

Chose: Min(EOLi)

Decision Analysis 3-36

18
 Expected Opportunity Loss
STATE OF NATURE
FAVORABLE UNFAVORABLE
ALTERNATIVE EOL
MARKET ($) MARKET ($)
Construct a large plant 0 180,000 90,000
Construct a small plant 100,000 20,000 60,000
Do nothing 200,000 0 100,000
Probabilities 0.50 0.50

Minimum EOL

Decision Analysis 3-37

Practice
Today’s Electronics specializes in manufacturing modern electronic components. It also builds
the equipment that produces the components. Phyllis Weinberger, who is responsible for
advising the president of Today’s Electronics on electronic manufacturing equipment, has
developed the following table concerning a proposed facility:

 What alternative would the firm choose to

maximize its expected profit (monetary value)?
 Calculate the expected value with perfect
information for this problem?
 Which alternative would result in the lowest
expected opportunity loss?
Probability 0.3 0.5 0.2

Decision Analysis 3-38

19
 Sensitivity Analysis
 Sensitivity analysis examines how the decision might change with
different input data.
 For the Thompson Lumber example:

P = probability of a favorable market

(1 – P) = probability of an unfavorable market

Decision Analysis 3-39

Sensitivity Analysis
EMV(Large Plant) = $200,000P – $180,000)(1 – P)
= $200,000P – $180,000 + $180,000P
= $380,000P – $180,000
EMV(Small Plant) = $100,000P – $20,000)(1 – P)
= $100,000P – $20,000 + $20,000P
= $120,000P – $20,000
EMV(Do Nothing) = $0P + 0(1 – P)
= $0

Decision Analysis 3-40

20
 Sensitivity Analysis
EMV Values

$300,000

$200,000 EMV (large plant)

Point 2

$100,000 EMV (small plant)

Point 1

0 EMV (do nothing)

1
–$100,000
Values of P

–$200,000

Decision Analysis 3-41

Sensitivity Analysis

Decision Analysis 3-42

21
 Sensitivity Analysis
BEST RANGE OF P
ALTERNATIVE VALUES
Do nothing Less than 0.167
Construct a small plant 0.167 – 0.615
Construct a large plant Greater than 0.615

Decision Analysis 3-43

Using Excel

Input Data for the Thompson Lumber Problem Using Excel QM

Decision Analysis 3-44

22
 Using Excel

Output Results for the Thompson Lumber Problem Using Excel QM

Decision Analysis 3-45

3.6 Decision Trees

 Any problem that can be presented in a decision table can
also be graphically represented in a decision tree.
 Decision trees are most beneficial when a sequence of
decisions must be made.
 All decision trees contain decision points or nodes, from which
one of several alternatives may be chosen.
 All decision trees contain state-of-nature points or nodes, out
of which one state of nature will occur.

Decision Analysis 3-46

23
 Five Steps of 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) for each state of nature node.

Decision Analysis 3-47

Structure of Decision Trees

 Trees start from left to right.

 Trees represent decisions and outcomes in sequential order.
 Squares represent decision nodes.
 Circles represent states of nature nodes.
 Lines or branches connect the decisions nodes and the states of
nature.

Decision Analysis 3-48

24
 Thompson’s Decision Tree
A State-of-Nature Node

Favorable Market
A Decision Node
1
Unfavorable Market

Favorable Market
Construct
Small Plant
2
Unfavorable Market

Decision Analysis 3-49

Thompson’s Decision Tree

EMV for Node 1 = (0.5)($200,000) + (0.5)(–$180,000)
= $10,000
Payoffs
Favorable Market (0.5)
$200,000
Alternative with best
EMV is selected 1
Unfavorable Market (0.5)
–$180,000

Favorable Market (0.5)

$100,000
Construct
Small Plant
2
Unfavorable Market (0.5)
–$20,000

EMV for Node 2 = (0.5)($100,000)

= $40,000 + (0.5)(–$20,000)

$0
Decision Analysis 3-50

25
 Additional Information
 Before deciding about building a new plant, John Thompson has the
option of conducting his own marketing research survey, at a cost of
$10,000.

 The information from his survey could help him decide whether to
construct a large plant, a small plant, or not to build at all.

 Develop Thompson’s complex decision tree:

 John Thompson has two decisions to make, with the second decision dependent on
the outcome of the first.

Decision Analysis 3-51

Thompson’s Complex Decision Tree

First Decision Second Decision
Point Point
Favorable Market (0.78)
2 Unfavorable Market (0.22)
Favorable Market (0.78)
Small
Plant
3 Unfavorable Market (0.22)

No Plant

1 Favorable Market (0.27)

4 Unfavorable Market (0.73)
Favorable Market (0.27)
Small
Plant
5 Unfavorable Market (0.73)

No Plant

Favorable Market (0.50)

6 Unfavorable Market (0.50)
Favorable Market (0.50)
Small
Plant
7 Unfavorable Market (0.50)

No Plant

Decision Analysis 3-52

26
 Thompson’s Complex Decision Tree

Decision Analysis 3-53

Thompson’s Complex Decision Tree

Decision Analysis 3-54

27
 Thompson’s Complex Decision Tree
First Decision Second Decision Payoffs
Point Point
$106,400 Favorable Market (0.78)
$190,000
Unfavorable Market (0.22)

$106,400
–$190,000
$63,600 Favorable Market (0.78)
Small $90,000
Unfavorable Market (0.22)
Plant –$30,000
No Plant
–$10,000
–$87,400 Favorable Market (0.27)
$190,000
Unfavorable Market (0.73)
–$190,000
$2,400 Favorable Market (0.27)

$2,400
Small $90,000
Unfavorable Market (0.73)
Plant –$30,000
No Plant
–$10,000
$49,200

$10,000 Favorable Market (0.50)

$200,000
Unfavorable Market (0.50)
–$180,000
$40,000

$40,000 Favorable Market (0.50)

Small $100,000
Unfavorable Market (0.50)
Plant –$20,000
No Plant
$0

Decision Analysis
The best choice is to seek marketing information. 3-55

Expected Value of Sample Information

 Suppose Thompson wants to know the actual value of

doing the survey.
Expected value Expected value
with sample of best decision
EVSI = information, assuming – without sample
no cost to gather it information

= (EV with sample information + cost)

– (EV without sample information)

Decision Analysis 3-56

28
 Sensitivity Analysis

 How sensitive are the decisions to changes in the

probabilities?
 How sensitive is our decision to the probability of a favorable survey
result?
 That is, if the probability of a favorable result (p = .45) where to
change, would we make the same decision?
 How much could it change before we would make a different
decision?

Decision Analysis 3-57

Sensitivity Analysis
p = probability of a favorable survey result
(1 – p) = probability of a negative survey result
EMV(node 1) = ($106,400)p +($2,400)(1 – p)
= $104,000p + $2,400
We are indifferent when the EMV of node 1 is the same as the EMV of not
conducting the survey, $40,000

$104,000p + $2,400 = $40,000

$104,000p = $37,600
p = $37,600/$104,000 = 0.36

Decision Analysis 3-58

29
 Practice

A group of medical professionals is considering the construction of a

private clinic. If the medical demand is high (i.e., there is a favorable
market for the clinic), the physicians could realize a net profit of $100,000.
If the market is not favorable, they could lose $40,000. Of course, they
don’t have to proceed at all, in which case there is no cost. In the absence
of any market data, the best the physicians can guess is that there is a 50–
50 chance the clinic will be successful. Construct a decision tree to help
analyze this problem. What should the medical professionals do?

Decision Analysis 3-59

Decision Analysis 3-60

30
 3.7 Bayesian Analysis
 There are many ways of getting probability data. It can be
based on:
 Management’s experience and intuition.
 Historical data.
 Computed from other data using Bayes’ theorem.
 Bayes’ theorem incorporates initial estimates and information
about the accuracy of the sources.
 It also allows the revision of initial estimates based on new
information.

Decision Analysis 3-61

Calculating Revised Probabilities

 In the Thompson Lumber case we used these four conditional

probabilities:
P (favorable market(FM) | survey results positive) = 0.78
P (unfavorable market(UM) | survey results positive) = 0.22
P (favorable market(FM) | survey results negative) = 0.27
P (unfavorable market(UM) | survey results negative) = 0.73

 But how were these calculated?

 The prior probabilities of these markets are:
(without any market survey information)

P (FM) = 0.50
P (UM) = 0.50
Decision Analysis 3-62

31
 Calculating Revised Probabilities
 Through discussions with experts Thompson has learned the information
in the table below:
STATE OF NATURE
RESULT OF SURVEY FAVORABLE MARKET UNFAVORABLE MARKET
(FM) (UM)

Positive (predicts favorable market for P (survey positive | FM) P (survey positive | UM)
product) = 0.70 = 0.20

Negative (predicts unfavorable market for P (survey negative | FM) P (survey negative | UM)
product) = 0.30 = 0.80

 He can use this information and Bayes’ theorem to calculate posterior

probabilities.
Decision Analysis 3-63

Calculating Revised Probabilities

 Recall Bayes’ theorem:

P ( B | A )  P ( A)
P( A | B) 
P ( B | A)  P ( A)  P ( B | A )  P ( A )

where
A, B  any two events
A   complement of A

For this example, A will represent a favorable market and B will represent a
positive survey.

Decision Analysis 3-64

32
 Calculating Revised Probabilities

 P (FM | survey positive)

P ( survey positive | FM )  P ( FM )

P(survey positive |FM)  P(FM)  P(survey positive |UM)  P(UM)

(0.70 )(0.50) 0.35

   0.78
(0.70)(0.50 )  (0.20)(0.50 ) 0.45

 P (UM | survey positive)

P ( survey positive | UM )  P (UM )

P(survey positive |UM)  P(UM)  P(survey positive |FM)  P(FM)

(0.20)(0.50 ) 0.10
   0.22
(0.20)(0.50 )  (0.70 )(0.50) 0.45
Decision Analysis 3-65

Calculating Revised Probabilities

Probability Revisions Given a Positive Survey

POSTERIOR PROBABILITY
CONDITIONAL
PROBABILITY P(STATE OF
P(SURVEY NATURE |
STATE OF PRIOR POSITIVE | STATE JOINT SURVEY
NATURE PROBABILITY OF NATURE) PROBABILITY POSITIVE)
FM 0.50 X 0.70 = 0.35 0.35/0.45 = 0.78
UM 0.50 X 0.20 = 0.10 0.10/0.45 = 0.22
P(survey results positive) = 0.45 1.00

Decision Analysis 3-66

33
 Calculating Revised Probabilities

 P (FM | survey negative)

P ( survey negative | FM )  P ( FM )

P(survey negative |FM)  P(FM)  P(survey negative |UM)  P(UM)

(0.30)(0.50 ) 0.15
   0.27
(0.30)(0.50 )  (0.80 )(0.50) 0.55

 P (UM | survey negative)

P ( survey negative | UM )  P (UM )

P(survey negative |UM)  P(UM)  P(survey negative |FM)  P(FM)

(0.80)(0.50 ) 0.40
   0.73
(0.80)(0.50 )  (0.30 )(0.50) 0.55

Decision Analysis 3-67

Calculating Revised Probabilities

Probability Revisions Given a Negative Survey

POSTERIOR PROBABILITY

CONDITIONAL
PROBABILITY P(STATE OF
P(SURVEY NATURE |
STATE OF PRIOR NEGATIVE | STATE JOINT SURVEY
NATURE PROBABILITY OF NATURE) PROBABILITY NEGATIVE)
FM 0.50 X 0.30 = 0.15 0.15/0.55 = 0.27

UM 0.50 X 0.80 = 0.40 0.40/0.55 = 0.73

P(survey results negative) = 0.55 1.00

Decision Analysis 3-68

34
 Using Excel
Formulas Used for Bayes’ Calculations in Excel

Program 3.2A
Decision Analysis 3-69

Using Excel
Results of Bayes’ Calculations in Excel

Decision Analysis 3-70

35
 Potential Problems Using Survey Results

 We can not always get the necessary data for analysis.

 Survey results may be based on cases where an action was
taken.
 Conditional probability information may not be as accurate as
we would like.

Decision Analysis 3-71

3.8 Utility Theory

 Monetary value is not always a true indicator of the overall

value of the result of a decision.

 The overall value of a decision is called utility.

 Economists assume that rational people make decisions to

maximize their utility.

Decision Analysis 3-72

36
 Utility Theory

 Your decision?
Suppose that you are the lucky holder of a lottery ticket.
Five minutes from now a fair coin could be flipped, and if it comes up tails,
you would win $5 million. If it comes up heads, you would win nothing.
Just a moment ago a wealthy person offered you $2 million for your ticket.
Let’s assume that you have no doubts about the validity of the offer. The
person will give you a certified check for the full amount, and you are
absolutely sure the check would be good.

Decision Analysis 3-73

Utility Theory
Your Decision Tree for the Lottery Ticket
$2,000,000
Accept
Offer
$0
Heads
Reject (0.5)
Offer

Tails
(0.5)

EMV = $2,500,000
$5,000,000

Decision Analysis 3-74

37
 Utility Theory
 Utility assessment
 assigns the worst outcome a utility of 0,
 the best outcome, a utility of 1.

 A standard gamble is used to determine utility values.

Decision Analysis 3-75

Standard Gamble for Utility Assessment

(p)
Best Outcome
Utility = 1
(1 – p)
Worst Outcome
Utility = 0

Other Outcome
Utility = ?
 When you are indifferent, your utility values are equal.
Expected utility of alternative 2 = Expected utility of alternative 1
Utility of other outcome = (p)(utility of best outcome, which is 1)
+ (1 – p)(utility of the worst outcome, which
is 0)
Utility of other outcome = (p)(1) + (1 – p)(0) = p
Decision Analysis 3-76

38
 Investment Example
 Jane Dickson wants to construct a utility curve revealing her
preference for money between $0 and $10,000.
 A utility curve plots the utility value versus the monetary value.
 An investment in a bank will result in $5,000.
 An investment in real estate will result in $0 or $10,000.
 Unless there is an 80% chance of getting $10,000 from the real
estate deal, Jane would prefer to have her money in the bank.
 So if p = 0.80, Jane is indifferent between the bank or the real estate
investment.

Decision Analysis 3-77

Investment Example
p = 0.80 $10,000
U($10,000) = 1.0

(1 – p) = 0.20 $0
U($0.00) = 0.0

$5,000
U($5,000) = p = 0.80

Utility for $5,000 = U($5,000) = pU($10,000) + (1 – p)U($0)

= (0.8)(1) + (0.2)(0) = 0.8

Decision Analysis 3-78

39
 Investment Example
 We can assess other utility values in the same way.
 For Jane these are:

Utility for $7,000 = 0.90

Utility for $3,000 = 0.50

 Using the three utilities for different dollar amounts, she can construct a
utility curve.

Decision Analysis 3-79

Utility Curve
1.0 –
U ($10,000) = 1.0

U ($7,000) = 0.90
0.9 –

0.8 –
U ($5,000) = 0.80

0.7 –

0.6 –
U ($3,000) = 0.50
Utility

0.5 –

0.4 –

0.3 –

0.2 –

0.1 –
U ($0) = 0
| | | | | | | | | | |
$0 $1,000 $3,000 $5,000 $7,000 $10,000

Monetary Value
Decision Analysis 3-80

40
 Utility Curve
 Jane’s utility curve is typical of a risk avoider.
 She gets less utility from greater risk.
 She avoids situations where high losses might occur.
 As monetary value increases, her utility curve increases at a slower rate.

 A risk seeker gets more utility from greater risk

 As monetary value increases, the utility curve increases at a faster rate.

 Someone with risk indifference will have a linear utility curve.

Decision Analysis 3-81

Preferences for Risk

Risk
Avoider
Utility

Risk
Seeker

Monetary Outcome
Decision Analysis 3-82

41
 Utility as a Decision-Making Criteria

 Once a utility curve has been developed it can be used in

making decisions.

 This replaces monetary outcomes with utility values.

 The expected utility is computed instead of the EMV.

Decision Analysis 3-83

Utility as a Decision-Making Criteria

 Mark Simkin loves to gamble.

 He plays a game tossing thumbtacks in the air.

 If the thumbtack lands point up, Mark wins $10,000.

 If the thumbtack lands point down, Mark loses $10,000.

 Mark believes that there is a 45% chance the thumbtack will

land point up.

 Should Mark play the game (alternative 1)?

Decision Analysis 3-84

42
 Utility as a Decision-Making Criteria

Decision Facing Mark Simkin

Decision Analysis 3-85

Utility as a Decision-Making Criteria

 Step 1– Define Mark’s utilities.

 Step 2 – Replace monetary values with utility values.

Decision Analysis 3-86

43
 Using Expected Utilities in Decision Making

E = 0.162 Tack Lands Utility

Point Up (0.45)
0.30

Tack Lands
Point Down (0.55)
0.05

Don’t Play
0.15

Decision Analysis 3-87

Utility Curve for Mark Simkin

1.00 –

0.75 –
Utility

0.50 –

0.30 –
0.25 –

0.15 –

0.05 –
0 |– | | | |
–$20,000 –$10,000 $0 $10,000 $20,000

Monetary Outcome

Decision Analysis 3-88

44
 Exercise
The Business Analytics department at State University will be signing a 3-year
lease for a new copy machine, and three different machines are being considered.
For each of these, there is a monthly fee, which includes service on the machine,
plus a charge for each copy. The number of copies that would be made each
month is uncertain, but the department has estimated that the number of copies
per month could be 10,000 or 20,000 or 30,000 per month. The monthly cost for
each machine based on each of the three levels of activity is shown below:

10,000 copies 20,000 copies 30,000 copies

per month per month per month
Machine A 950 1,050 1,150
Machine B 850 1,100 1,350
Machine C 700 1,000 1,300
Probabilities 0.4 0.3 0.3
Decision Analysis 3-89

45