Week 13

Decision Making

Week 13-1

Week 13 - Learning Objectives

Describe basic features of decision making

Construct a payoff table and an opportunity-loss
table

Define and apply the expected value criterion for
decision making

Compute the value of perfect information

Describe utility and attitudes toward risk

Week 13-2

Steps in Decision Making

List Alternative Courses of Action (Options)

Choices or actions

List Uncertain Events

Possible events or outcomes

Determine Payoffs

Associate a Payoff with Each Event/Outcome combination

Adopt Decision Criteria

Evaluate Criteria for Selecting the Best Course of Action
(Option)

Choose the best option.

Week 13-3

List Possible Actions (Options) and

Events
Two Methods
of Listing

Table
Payoff

Decision Tree
Opportunity Loss

Payoff

Week 13-4

A Payoff Table
A payoff table shows alternatives,
states of nature, and payoffs

Investment
Choice
(Action)
Large factory
Average factory
Small factory

Profit in $1,000s
(Events / States of Nature)
Strong
Stable
Weak
Economy
Economy
Economy
200
90
40

50
120
30

-120
-30
20

Week 13-5

Opportunity Loss
Opportunity loss is the difference between an actual
payoff for an action and the optimal payoff, given a
particular event / state of nature
Investment
Choice
(Action)
Large factory
Average factory
Small factory

Payoff
Table

Profit in $1,000s
(Events)
Strong
Economy

Stable
Economy

Weak
Economy

200
90
40

50
120
30

-120
-30
20

The action Average factory has payoff 90 for Strong Economy. Given
Strong Economy, the choice of Large factory would have given a
payoff of 200, or 110 higher. Opportunity loss = 110 for this cell.
Week 13-6

Opportunity Loss Table

(continued)
Investment
Choice
(Action)
Large factory
Average factory
Small factory

Payoff
Table

Profit in $1,000s
(States of Nature)
Strong
Economy

Stable
Economy

Weak
Economy

200
90
40

50
120
30

-120
-30
20

Investment
Choice
(Action)
Large factory
Average factory
Small factory

Build
Opportunity
Loss Table

Opportunity Loss in $1,000s

(Events)
Strong
Economy

Stable
Economy

Weak
Economy

0
110
160

70
0
90

140
50
0
Week 13-7

A Decision Tree
Large factory

Average factory

Small factory

Strong Economy

200

Stable Economy

50

Weak Economy

-120

Strong Economy

90

Stable Economy

120

Weak Economy

-30

Strong Economy

40

Stable Economy

30

Weak Economy

20

Payoffs
Week 13-8

Decision Criteria

The Maximum Expected
Monetary Value (EMV)

The Minimum Expected
Opportunity Loss (EOL)
= Expected Value of
Perfect Information
(EVPI)

The Minimum Coefficient

of variation (CV)

The Maximum Return to
risk ratio (RRR)

Disadvantages:
The risk or
variability of certain
option is not
taken into account.

Advantages:
The risk or
variability of certain
option is
taken into account.
Week 13-9

Common Decision Criteria

Based on Expected Monetary Value (EMV)

Choose the maximum expected profit for taking
action Aj.

Based on Expected Opportunity Loss (EOL)

Choose the minimum expected opportunity loss for
taking action Aj.

Expected Value of Perfect Information (EVPI) is
the expected opportunity loss from the best decision

Week 13-10

Expected Monetary Value

Solution
Goal: Maximize expected value

The expected monetary value is the weighted

average payoff, given specified probabilities
for each event
N

EMV( j) = x ijPi
i=1

Where EMV(j) = expected monetary value of action j

xij = payoff for action j when event i occurs
Pi = probability of event i
Week 13-11

Expected Monetary Value

Solution
(continued)

The expected value is the weighted average

payoff, given specified probabilities for each event
Profit in $1,000s
(Events)
Investment
Choice
(Action)
Large factory
Average factory
Small factory

Strong
Economy
(0.3)

Stable
Economy
(0.5)

Weak
Economy
(0.2)

200
90
40

50
120
30

-120
-30
20

Suppose these
probabilities
have been
assessed for
these three
events
Week 13-12

Expected Monetary Value

Solution
(continued)

Goal: Maximize expected value

Payoff Table:
Profit in $1,000s
(Events)
Investment
Choice
(Action)
Large factory
Average factory
Small factory

Strong
Economy
(0.3)

Stable
Economy
(0.5)

Weak
Economy
(0.2)

200
90
40

50
120
30

-120
-30
20

Expected
Values
(EMV)
61
81
31

Maximize
expected
value by
choosing
Average
factory

Example: EMV (Average factory) = 90(0.3) + 120(0.5) + (-30)(0.2)

= 81
Week 13-13

Decision Tree Analysis

A Decision tree shows a decision problem,
beginning with the initial decision and ending
will all possible outcomes and payoffs.
Use a square to denote decision nodes
Use a circle to denote uncertain events

Week 13-14

Add Probabilities and Payoffs

(continued)
Strong Economy (0.3) 200

Large factory

Stable Economy (0.5)

Weak Economy

(0.2) -120

Strong Economy (0.3)

Average factory

Decision
Small factory

50

90

Stable Economy (0.5) 120

Weak Economy (0.2) -30
Strong Economy (0.3)

40

Stable Economy (0.5)

30

Weak Economy

(0.2)

20

Uncertain Events
Probabilities Payoffs
Week 13-15

Fold Back the Tree

EMV=200(.3)+50(.5)+(-120)(.2)=61

Large factory

Strong Economy (0.3) 200

Stable Economy (0.5)
Weak Economy

EMV=90(.3)+120(.5)+(-30)(.2)=81

Average factory

EMV=40(.3)+30(.5)+20(.2)=31

Small factory

50

(0.2) -120

Strong Economy (0.3)

90

Stable Economy (0.5) 120

Weak Economy (0.2) -30
Strong Economy (0.3)

40

Stable Economy (0.5)

30

Weak Economy

(0.2)

20

Week 13-16

Make the Decision

EV=61

Large factory

Strong Economy (0.3) 200

Stable Economy (0.5)
Weak Economy

EV=81

Average factory

EV=31

Small factory

50

(0.2) -120

Strong Economy (0.3)

90

Stable Economy (0.5) 120

Weak Economy (0.2) -30
Strong Economy (0.3)

40

Stable Economy (0.5)

30

Weak Economy

(0.2)

Maximum
EMV=81

20

Week 13-17

Expected Opportunity Loss

Solution
Goal: Minimize expected opportunity loss

The expected opportunity loss is the weighted

average loss, given specified probabilities for
each event
N

EOL( j) = L ijPi
i=1

Where EOL(j) = expected monetary value of action j

Lij = opp. loss for action j when event i occurs
Pi = probability of event i
Week 13-18

Expected Opportunity Loss

Solution
Goal: Minimize expected opportunity loss
Opportunity Loss Table
Opportunity Loss in $1,000s
(Events)
Investment
Choice
(Action)
Large factory
Average factory
Small factory

Strong
Economy
(0.3)

Stable
Economy
(0.5)

Weak
Economy
(0.2)

0
110
160

70
0
90

140
50
0

Expected
Op. Loss
(EOL)
63
43
93

Minimize
expected
op. loss by
choosing
Average
factory

Example: EOL (Large factory) = (0)(0.3) + (70)(0.5) + (140)(0.2)

= 63
Week 13-19

The Value of Information

Expected Value of Perfect Information, EVPI
Expected Value of Perfect Information
EVPI = Expected monetary value under certainty
Expected monetary value under
uncertainty (the best alternative)

(EVPI is equal to the minimum expected

opportunity loss ( from the best decision)

Week 13-20

Expected Profit Under Certainty

Expected
profit under
certainty
= expected
value of the
best
decision,
given perfect
information

Profit in $1,000s
(Events)
Investment
Choice
(Action)

Strong
Economy
(0.3)

Stable
Economy
(0.5)

Weak
Economy
(0.2)

200
90
40

50
120
30

-120
-30
20

Value of best decision

200
for each event:

120

20

Large factory
Average factory
Small factory

Example: Best decision

given Strong Economy is
Large factory
Week 13-21

Expected Profit Under Certainty

(continued)
Profit in $1,000s
(Events)
Investment
Choice
(Action)

Now weight
these outcomes
with their
probabilities to
find the
expected value:

Large factory
Average factory
Small factory

Strong
Economy
(0.3)

Stable
Economy
(0.5)

Weak
Economy
(0.2)

200
90
40

50
120
30

-120
-30
20

200

120

20

200(0.3)+120(0.5)+20(0.2)
= 124

Expected
profit under
certainty
Week 13-22

The Value of Information Solution

Expected Value of Perfect Information (EVPI)
EVPI = Expected monetary value under certainty
Expected monetary value under uncertainty (the best
alternative)
Recall:

Expected profit under certainty = 124

EMV is maximized by choosing Average factory,
where EMV = 81

so:

EVPI = 124 81
= 43

(EVPI is the maximum amount of value that you would be

willing to spend to obtain perfect information)
Week 13-23

Coefficient of variation (CV):

Accounting for Variability

is the standard deviation for certain option.

Min CV j =

j
EMV j

100%

is the expected monetary value for certain option.

Week 13-24

Coefficient of variation (CV):

Accounting for Variability

(continued)

Example:

Consider the choice of Stock A vs. Stock B

Percent Return
(Events)
Stock Choice
(Action)

Strong
Economy
(0.7)

Weak
Economy
(0.3)

Stock A

30

-10

18.0

Stock B

14

12.2

Expected
Return:
Stock A has a higher
EMV, but what about
risk?

Week 13-25

Coefficient of variation (CV):

Accounting for Variability

(continued)

Calculate the variance and standard deviation for

Stock A and Stock B:
Percent Return
(Events)
Stock Choice
(Action)

Strong
Economy
(0.7)

Weak
Economy
(0.3)

Stock A

30

-10

18.0

336.0

18.33

Stock B

14

12.2

7.56

2.75

Expected
Standard
Return:
Variance: Deviation:

N
2
2
2
Example: = ( X i ) P( X i ) = (30 18) (0.7) + (10 18) (0.3) = 336.0
2
A

i =1

Week 13-26

Coefficient of variation (CV):

Accounting for Variability

(continued)

Calculate the coefficient of variation for each stock:

CVA =

A
18.33
100% =
100% = 101.83%
EMVA
18.0

B
2.75
CVB =
100% =
100% = 22.54%
EMVB
12.2

Stock A has
much more
relative
variability
Choose stock B
because CVB is
lesser than CVA.

Week 13-27

Return-to-Risk Ratio (RRR)

Return-to-Risk Ratio (RTRR):

EMV(j)
RRR(j) =
j

Expresses the relationship between the return
(expected payoff) and the risk (standard deviation)

Week 13-28

Return-to-Risk Ratio
EMV(j)
RRR(j) =
j

RRR(A) =

EMV(A) 18.0
=
= 0.982
A
18.33

EMV(B) 12.2
RRR(B) =
=
= 4.436
B
2.75

You might want to consider Stock B if you dont

like risk. Although Stock A has a higher Expected
Return, Stock B has a much larger return to risk
ratio and a much smaller CV
Week 13-29

Decision Making
with Sample Information
Prior
Probability

Permits revising old

probabilities based on new
information

New
Information
Revised
Probability

Week 13-30

Bayes Theorem for the

Revision of Probability
In the 1700s, Thomas Bayes developed a
way to revise the probability that a first
event occurred from information obtained
from a second event.
Bayes Theorem: For two events A and B
P( A| B) = P( A and B)
P(B)
P( A)P(B| A)
=
[P( A)P(B| A)] + [P( A')P(B| A')]
Copyright 2005 Brooks/Cole, a division of Thomson Learning,
Inc.
Week 13-31

Bayes Theorem
P(A | Bi )P(Bi )
P(Bi | A) =
P(A | B1)P(B1) + P(A | B2 )P(B2 ) + + P(A | Bk )P(Bk )

where:
Bi = ith event of k mutually exclusive and collectively
exhaustive events
A = new event that might impact P(Bi)

Week 13-32

Revised Probabilities
Example
Additional Information: Economic forecast is strong economy

When the economy was strong, the forecaster was correct
90% of the time.

When the economy was weak, the forecaster was correct
30% of the time.
F1 = the forecast is strong economy
F2 = weak forecast
E1 = strong economy = 0.70

Prior probabilities
from stock choice
example

E2 = weak economy = 0.30

P(F1 | E1) = 0.90

P(F1 | E2) = 0.30

Week 13-33

Revised Probabilities
Example
(continued)

P(F1 | E1 ) = .9 , P(F1 | E 2 ) = .3
P(E1 ) = .7 , P(E2 ) = .3

Revised Probabilities (Bayes Theorem)

P(E1 )P(F1 | E1 )
(.7)(.9)
P(E1 | F1 ) =
=
= .875
P(F1 )
(.7)(.9) + (.3)(.3)
P(E 2 )P(F1 | E 2 )
P(E 2 | F1 ) =
= .125
P(F1 )
Week 13-34

Revised Probabilities
Example
(continued)

Event
E1 (strong
economy)
E2 (weak
economy)

Prior
Prob.
P(Ei)
0.70
0.30

Conditional
Prob.
P(F1 | Ei)

Joint
Prob.
P(F1 Ei)

Revised
Prob.
P(Ei | F1)

0.90

0.70.9 =
0.63

0.63 / 0.72 =
0.875

0.30

0.30.3 =
0.09

0.09 / 0.72 =
0.125

P(F1) = 0.72

Where F1 = the forecast is strong economy

Week 13-35

Accounting for Variability with

Revised Probabilities
Calculate the variance and standard deviation for
Stock A and Stock B:
Percent Return
(Events)
Stock Choice
(Action)

Strong
Economy
(0.875)

Weak
Economy
(0.125)

Stock A

30

-10

25.0

175.0

13.229

Stock B

14

13.25

3.94

1.984

Expected
Standard
Return:
Variance: Deviation:

N
2
2
2
Example: = ( Xi ) P( X i ) = (30 25) (0.875) + (10 25) (0.125) = 175.0
2
A

i =1

Week 13-36

Accounting for Variability with

Revised Probabilities
(continued)

The coefficient of variation for each stock using the

results from the revised probabilities:
A
13.229
CVA =
100% =
100% = 52.92%
EMVA
25.0

B
1.984
CVB =
100% =
100% = 14.97%
EMVB
13.25

Week 13-37

Return-to-Risk Ratio with

Revised Probabilities
EMV(A)
25.0
RTRR(A) =
=
= 1.890
A
13.229

EMV(B) 13.25
RTRR(B) =
=
= 6.678
B
1.984
With the revised probabilities, both stocks have
higher expected returns, lower CVs, and larger
return to risk ratios

Week 13-38

Past Year Question

(April 2005 Q2a)
ABC Restaurant would like to determine
whether it would be profitable to establish a new
branch in Sungai Long. The manager believes
that there are three possible levels of demand
for this services: low, moderate and high
demand levels. Based on the past experience in
Kajang branch, the manager expects the
following probabilities to the various demand
levels:

Week 13-39

Past Year Question

(April 2005 Q2a)
P(L) = 0.2, P(M) = 0.5, P(H) = 0.3
Where L = low demand; M = moderate demand;
H = high demand
The manager has reported the following profits or
losses of this restaurant service for each
demand level (over a period of 6 months):

Week 13-40

Past Year Question

(April 2005 Q2a)
Action
Demand

Establish
restaurant ($)

Do not establish
restaurant ($)

Low (0.2)

-15,000

Moderate (0.5)

20,000

High (0.3)

60,000

Week 13-41

Past Year Question

(April 2005 Q2a)
i.

Calculate the expected monetary value (EMV)

for both actions.
ii. Compute the expected opportunity loss (EOL)
for both actions.
iii. Calculate the return-to-risk for establishing
this restaurant.
iv. Based on the results of (i) or (ii) and (iii),
should the manager establish this restaurant?
Why?
Week 13-42

Past Year Question

(April 2005 Q2a)

(i) EMV (restaurant) = (0.2)(-15,000) + (0.5)(20,000)

+ (0.3)(60,000) = $ 25,000
EMV (no restaurant) = $ 0

Week 13-43

Past Year Question

(April 2005 Q2a)
Opportunity Loss Table
Action
Demand

Establish
restaurant ($)

Do not establish
restaurant ($)

Low (0.2)

15,000

Moderate (0.5)

20,000

High (0.3)

60,000
Week 13-44

Past Year Question

(April 2005 Q2a)

(ii) EOL (restaurant) = (0.2)(15,000) + (0.5)(0) +

(0.3)(0) = $ 3,000
EOL (no restaurant) = (0. 2)(0) + (0.5)(20,000) +
(0.3)(60,000) = $ 28,000

Week 13-45

Past Year Question

(April 2005 Q2a)
(iii) Return-to-risk, RRR =

EMVi

i
Restaurant
0.2(15000 25000) 2

No Restaurant

= $0

= + 0.5(20000 25000) 2
+ 0.3(60000 25000) 2
= $26,457.51

Week 13-46

Past Year Question

(April 2005 Q2a)
Restaurant

No Restaurant

25000
RRR =
= 0.9449
26457.51

RRR = 0

(iv) Based on EMV, EOL and RRR, the manager

should establish a restaurant in Sungai Long.

Week 13-47

Summary

Described the payoff table and decision trees

Opportunity loss

Provided criteria for decision making

Expected monetary value

Expected opportunity loss

Return to risk ratio

Introduced expected profit under certainty and the

value of perfect information

Discussed decision making with sample
information

Addressed the concept of utility
Week 13-48