Decision Analysis: Optimize Your Decision-Making

1
Textbook: pp. 81-128
Chapter 3: Decision Analysis

2
Learning Objectives
After completing this chapter, students will be able to:

• List the steps of the decision-making process.
• Describe the types of decision-making environments.
• Make decisions under uncertainty.
• Use probability values to make decisions under risk.
• Use computers to solve basic decision-making problems.
• Develop accurate and useful decision trees.
• Revise probabilities using Bayesian analysis.
• Understand the importance and use of utility theory in
decision making.
3
雷军
Introduction
• What is involved in making a good decision?
2015
• 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 applies a quantitative approach
4
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

5
Thompson Lumber Company (1 of 3)
Step 1 – Define the problem

• Consider 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
Step 3 – Identify possible outcomes, states of nature

• The market could be favourable or unfavourable
6
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 ( NEXT SLIDE)
Step 5 – Select the decision model

• Depends on the environment and amount of risk and
uncertainty
Step 6 – Apply the model to the data

7
Decision Table = Payoff Table

We have no control
over this part!
Decision Table with Conditional Values for Thompson

Lumber
We have control over
this part!
Note: It is important to include all alternatives, including

“do nothing.”
8
Types of Decision-Making Environments
• Decision making under certainty

o The decision maker knows with certainty the
consequences of every alternative or decision
choice
• Decision making under uncertainty

o The decision maker does not know the probabilities
of the various outcomes
• Decision making under risk

o The decision maker knows the probabilities of the
various outcomes
9
Decision Making Under Uncertainty
Several states of nature exist and a manager cannot

assess the outcome probability with confidence or
when virtually no probability data are available:
• Criteria for making decisions under uncertainty:
1. Maximax (optimistic) Profit
2. Maximin (pessimistic)
3. Criterion of realism (Hurwicz)
Cost
4. Equally likely (Laplace)
5. Minimax regret
10
Optimistic
• Used to find the alternative that maximises the

maximum payoff – maximax criterion
o Locate the maximum payoff for each alternative
o Select the alternative with the maximum number
Thompson’s Maximax Decision
11
Pessimistic
• Used to find the alternative that maximises the minimum

payoff – maximin criterion
• Locate the minimum payoff for each alternative
• Select the alternative with the maximum number
Thompson’s Maximin Decision
12
α measures the degree of optimism!
Criterion of Realism (Hurwicz) (1 of 2)
• Often called weighted average
The advantage of this approach is that it

allows the decision maker to build in
relative
• Compromise between optimism and pessimism
• Select a coefficient of realism α, with 0 ≤ α ≤ 1
about
optimism and pessimism!!!
α = 1 is perfectly optimistic
α = 0 is perfectly pessimistic
feelings
• Compute the weighted averages for each alternative
• Select the alternative with the highest value
personal
Weighted average = α(best in row)
+ (1−α)(worst in row)
13
Weighted average = α(best in row) + (1−α)(worst in row)
Criterion of Realism (Hurwicz) (2 of 2)
For the large plant alternative using α = 0.8

(0.8)(200,000) + (1−0.8)(−180,000) = 124,000
For the small plant alternative using α = 0.8
(0.8)(100,000) + (1−0.8)(−20,000) = 76,000
Thompson’s Criterion of Realism Decision
14
The equally likely approach assumes that all probabilities of occurrence for
the states of nature are equal, and thus each state of nature is equally likely.
Equally Likely (Laplace)
• Considers all the payoffs for each alternative

o Find the average payoff for each alternative
o Select the alternative with the highest average
Thompson’s Equally Likely Decision: 200,000 * 0.5 +

(-180,000) * 0.5 =
15
Minimax Regret (1 of 4)
• Based on opportunity loss or regret

o The difference between the optimal profit and actual
payoff for a decision (Opportunity loss is the amount lost
by not picking the best alternative in a given state of
nature!)
1. Create an opportunity loss table by determining the

opportunity loss from not choosing the best alternative
2. Calculate opportunity loss by subtracting each payoff in

the column from the best payoff in the column
3. Find the maximum opportunity loss for each alternative

and pick the alternative with the minimum number
16
Determining Opportunity Losses for Thompson Lumber:

17
Opportunity Loss Table for Thompson Lumber:

18
Question: Can the opportunity loss be negative?
Thompson’s Minimax Decision Using Opportunity Loss:

19
EMV(alternative) = Sum of possible payoffs of the alternative,
each weighted by the probability of they payment occurring!
Decision Making Under Risk (1 of 2)

Our Manager‘s
assumption!
• When there are several possible states of nature and
the probabilities associated with each possible state
are known
o Most popular method – choose the alternative with
the highest expected monetary value (EMV)
EMV  alternative  =  X i P  X i 
where
Xi = payoff for the alternative in state of nature i
P(Xi) = probability of achieving payoff Xi (i.e.,
probability of state of nature i)
∑ = summation symbol
20
Decision Making Under Risk (2 of 2)
Expanding the equation:

EMV (alternative i) = (payoff of first state of nature)
×(probability of first state of nature)
+ (payoff of second state of nature)
×(probability of second state of nature)
+ … + (payoff of last state of nature)
×(probability of last state of nature)
21
EMV for Thompson Lumber (1 of 2)

Our Manager‘s
assumption!
• Each market outcome has a probability of occurrence of
0.50
• Which alternative would give the highest EMV?
EMV (large plant) = ($200,000)(0.5) + (−$180,000)(0.5)

= $10,000
EMV (small plant) = ($100,000)(0.5) + (−$20,000)(0.5)

= $40,000
EMV (do nothing) = ($0)(0.5) + ($0)(0.5)

= $0
22
Alternative with the largest expected monetary value (EMV) is
chosen!
EMV for Thompson Lumber (2 of 2)
Decision Table with Probabilities and EMVs for Thompson

Lumber:
23
Expected Value of Perfect Information (EVPI)

(1 of 8)
• Mr. Thompson has been approached by ‘Scientific Marketing

(SM)’, a firm that proposes to help him make the decision
about whether to build the plant to produce storage sheds.
• SM claims that its technical analysis will tell Mr. Thompson
with certainty whether the market is favourable for his
proposed product (environment changes from one of
decision making under risk to one of decision making
under certainty)!
• This information could prevent Mr. Thompson from making a
very expensive mistake. SM would charge Mr. Thompson
$65,000 for the information.
• Should Thompson Lumber purchase the information? Is it
worth $65,000 or what would it be worth?
24

(2 of 8)
• EVPI (expected value of perfect information) places an

upper bound on what you should pay for additional
information
• EVwPI (expected value with perfect information) is the

long run average return if we have perfect information
before a decision is made
EVwPI = ∑(best payoff in state of nature i) (probability of state of nature i)
25
The expected value of perfect information (EVPI) is the expected value
with perfect information minus the expected value without prefect
information.

(3 of 8)
• Expanded EVwPI becomes
EVwPI = (best payoff for first state of nature)

× (probability of first state of nature)
+ (best payoff for second state of nature)
× (probability of second state of nature)
+ … + (best payoff for last state of nature)
× (probability of last state of nature)
And
EVPI = EVwPI − Best EMV without perfect information
EVPI is the improvement in EMV that results from having perfect information!
26

(4 of 8)
Decision Table with Perfect Information:

Step 1: Calculate the EMV
for each alternatives given
our probabilities:
Expected Monetary Value

27

(5 of 8)

Step 2: Maximum EMV
without additional
information is found

28

(6 of 8)

Step 3: Best payoff in each
state of nature is found

29

(7 of 8)

Step 4: Expected value
with perfect information is
computed
EVwPI = ∑(best payoff in state of nature i) (probability of state of nature i)=

= 200,000 × 0.5 + 0 × 0.5 = 100,000
30

(8 of 8)
• The maximum EMV without additional information is

$40,000
EVPI = EVwPI − Maximum EMV without perfect information

= $100,000 − $40,000
= $60,000
 So the maximum Thompson should pay for the

additional information is $60,000.
 Thompson should not pay $65,000 for this information!
31
An alternative approach to maximising EMV is to minimise
expected opportunity loss (EOL).
Expected Opportunity Loss (1 of 2)
• Expected opportunity loss (EOL) is the cost of not

picking the best solution
o Construct an opportunity loss table
o For each alternative, multiply the opportunity
loss by the probability of that loss for each
possible outcome and add these together
o The minimum EOL will always result in the same
decision as maximum EMV, and
o that the EVPI will always equal the minimum EOL.
32
Opportunity Loss Table (1 of 2)
Determining Opportunity Losses for Thompson Lumber:
Opportunity loss – the difference between the optimal payoff for a given
state of nature and the actual payoff received for a particular decision.
It is the amount lost by not picking the best alternative in a given state of
nature.
33
Opportunity Loss Table (2 of 2)
Opportunity Loss Table for Thompson Lumber:

34
For each alternative, multiply the opportunity loss by the probability of
that loss for each possible outcome and add these together!
Expected Opportunity Loss (2 of 2)
EOL (large plant) = (0.50)($0) + (0.50)($180,000) = $90,000

EOL (small plant) = (0.50)($100,000) + (0.50)($20,000) = $60,000
EOL (do nothing) = (0.50)($200,000) + (0.50)($0) = $100,000
EOL Table for Thompson Lumber: Please recall – the

EVPI for the
Thompson case
was: $60,000
35
Sensitivity analysis examines how our decision might change with
different input data.
Sensitivity Analysis (1 of 4)
Define P = probability of a favourable market
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

36
EMV(large plant) = $380,000P − $180,000
EMV(small plant) = $120,000P − $20,000
EMV(do nothing) = $0
37
EMV(large plant) = $380,000P − $180,000
EMV(small plant) = $120,000P − $20,000
EMV(do nothing) = $0
Point 1: EMV(do nothing) = EMV(small plant)
Point 2: EMV(small plant) = EMV(large plant)

38
39
A Minimisation Example (1 of 10)
• The following example illustrates how the decision-making

criteria are applied to problems in which the payoffs are costs
that should be minimised.
The Business Analytics department of Henan University of Technology

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.
40
Payoff Table with Monthly Copy Costs for Business

Analytics Department:
Which machine should be selected?

41
Best and Worst Payoffs (Costs) for Business Analytics

Department:
• If the decision maker is optimistic, only the best (minimum) payoff for
each decision is considered. The BEST (minimum) of these is 700. Thus
machine C would be selected.
• If the decision maker is pessimistic, only the worst (maximum) payoff for
each decision is considered – and the BEST of these is 1,150. Thus
machine A would be selected.
42

Our assumption!
• Using Hurwicz criteria with 70% coefficient of realism

Weighted average = 0.7(best payoff) + (1 − 0.7)(worst payoff)
For each machine:

Machine A: 0.7(950) + 0.3(1,150) = 1,010
Machine B: 0.7(850) + 0.3(1,350) = 1,000
Machine C: 0.7(700) + 0.3(1,300) = 880
The decision would be to select Machine C because it has the lowest

weighted average cost!
43
• For equally likely criteria

Average payoff for each machine:
Machine A: (950 + 1,050 + 1,150)÷3 = 1,050
Machine B: (850 + 1,100 + 1,350)÷3 = 1,100
Machine C: (700 + 1,000 + 1,300)÷3 = 1,000
Based on the equally likely criterion: Machine C would be selected

because it has the lowest average cost!
44
• For EMV criteria probabilities must be known for each

state of nature:
State of nature 1:
State of nature 2:
State of nature 3:
We can now use these probabilities to calculate the EMVs!

45
• For EMV criteria EMV  alternative  =  X i P  X i 
Expected Monetary Values and Expected Values with

Perfect Information for Business Analytics Department:
Machine C would be selected because it has the lowest EMV!

46
Perfect information would lower the expected value by $45!

• For EMV criteria

 To find the EVPI, we first find the payoffs (costs) that would be
experienced with perfect information!
 The best payoff in each state of nature is the lowest value (cost) in
the state of nature!
EVwPI = $700*0.4 + $1,000*0,3 + $1,150*0.3 = $925

Best EMV without perfect information = $970 EVPI = $970 − $925 = $45
47
• Opportunity loss criteria

We must first develop the opportunity loss table:
• In each state of nature, the opportunity loss indicates how much worse each
payoff is than the best possible payoff in that state of nature!
• The best payoff would be the lowest cost! We subtract the lowest value in each
column from all the values in that column!
48
EOL (Machine A) = 0.4*250 + 0.3*50 + 0.3*0 = 115
EOL (Machine B) = 0.4*150 + 0.3*100 + 0.3*200 = 150
EOL (Machine C) = 0.4*0 + 0.3*0 + 0.3*150 = 45
• Opportunity loss criteria

We must first develop the opportunity loss table:
• Once the opportunity loss table has been developed, the minimax regret criterion
is applied! The maximum regret for each alternative is found, and the alternative
with the minimum of these maximums is selected!  We select Machine C!
• The probabilities are used to compute the expected opportunity losses!

Machine C has the lowest EOL of $45, so it would be selected based on the
minimum EOL criterion!
49
PROGRAMME 3.1A
Use File: 3.3.dec
Using Software (1 of 3)
QM for Windows Input for Thompson Lumber Example:

Step 1
Step 2
Step 3
50
PROGRAMME 3.1B
QM for Windows Input for Thompson Lumber Example:

Enter data into table and type
the row and column names
51
PROGRAMME 3.1C
QM for Windows Output Screen for Thompson Lumber

Example: Click Window to see
more information (e.g. EVPI
and opportunity loss results)
52
PROGRAMME 3.2A
Using Excel 2016 (1 of 3)
Excel QM Results for Thompson Lumber Example:

Please open the Excel
QM v5.2 file on your
desktop!
53
PROGRAMME 3.2A
Excel QM Results for Thompson Lumber Example:
To see the
formulas, hold
down the control
key (Ctrl) and
press the ‘ (grave
accent) key
54
PROGRAMME 3.2B
Key Formulas in Excel QM for Thompson Lumber

Example:
55
Decision Trees
• Any problem that can be presented in a decision table

can be graphically represented in a decision tree
o All decision trees contain decision points/nodes and
state-of-nature points/nodes
• At decision nodes one of several alternatives
may be chosen
• At state-of-nature nodes one state of nature will
occur
o Most beneficial when a sequence of decisions must

be made!
56
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
57
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
58
At decision nodes one of several alternatives may be chosen!
At state-of-nature nodes one state of nature will occur!
Thompson’s Decision Tree (1 of 2)

59
Thompson’s Decision Tree (2 of 2)
Completed and Solved Decision Tree for Thompson

Lumber:
The branch leaving

the decision node
leading to the state-
of-nature node with
the highest EMV
should be chosen.
 A small plant
should be built!
60
Thompson’s Complex Decision Tree (1 of 6)

- sequential decisions need to be made -
Let’s say that Mr. Thompson has two decisions to make,
with the second decision dependent on the outcome of
the first.
Before deciding about building a new plant, Mr. 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. Mr. Thompson recognises that such a market
survey will not provide him with perfect information,
but it may help quite a bit nevertheless.
61
At decision nodes one of several alternatives may be chosen!
At state-of-nature nodes one state of nature will occur!

Larger Decision
Tree with Payoffs
and Probabilities
for Thompson
Lumber:
62
Probability Rules
• Conditional probability – probability that an event

occurs given another event has already happened
P(AB)
P(A | B) =
P(B)
P(AB) = P(A | B) P(B)

o Probability of a 7 given a heart has been drawn
P(AB) 1/
52
P(A | B) = = 13/
= 1/13
P(B) 52
63

1. Given favourable survey results
EMV(node 2) = EMV(large plant | positive survey)

= (0.78)($190,000) + (0.22)(−$190,000)
= $106,400
EMV(node 3) = EMV(small plant | positive survey)

= (0.78)($90,000) + (0.22)(−$30,000)
= $63,600
EMV for no plant = −$10,000

 If the survey results are favourable, a large plant should be built!
64
2. Given negative survey results
EMV(node 4) = EMV(large plant | negative survey)

= (0.27)($190,000) + (0.73)(−$190,000)
= −$87,400
EMV(node 5) = EMV(small plant | negative survey)

= (0.27)($90,000) + (0.73)(−$30,000)
= $2,400
EMV for no plant = −$10,000

 Given a negative survey result a small plant should be built!
65
3. Expected value of the market survey

EMV(node 1) = EMV(conduct survey)
= (0.45)($106,400) + (0.55)($2,400)
= $47,880 + $1,320 = $49,200
4. Expected value no market survey
EMV(node 6) = EMV(large plant)
= (0.50)($200,000) + (0.50)(−$180,000)  Building a small
plant is the best
= $10,000
choice, given that
EMV(node 7) = EMV(small plant) the marketing
= (0.50)($100,000) + (0.50)(−$20,000) research is not
performed.
= $40,000
EMV for no plant = $0
66
NOTICE: On the tree that a pair of slash lines “/ /” through a decision branch
indicates that a particular alternative is dropped from further consideration. This is
because its EMV is lower than the EMV for the best alternative!
Thompson’s Decision Tree with EMVs Shown:

We move back to the first decision
node and choose the best alternative:
 The expected monetary value of

conducting the survey is $49,200,
versus an EMV of $40,000 for not
conducting the study, so the best
choice is to seek marketing
information.
• If the survey results are

favourable we should construct a
large plant!
• But if the research is negative, he
should construct a small plant!
67
Expected Value of Sample Information (1 of 2)
• Mr. Thompson now realises that conducting the

market research is not free!
 He would like to know what the actual value of doing a

survey is!
• One way of measuring the value of market information

is to compute the expected value of sample
information (EVSI) which is the increase in expected
value resulting from the sample information.
68
Expected Value of Sample Information (2 of 2)
• Thompson wants to know the actual value of doing

the survey: cost for conducting the survey
EVSI = (EV with SI + cost) − (EV without SI)

where:
EVSI = expected value of sample information
EV with SI = expected value with sample information
EV without SI = expected value without sample information
EVSI = ($49,200 + $10,000) − $40,000 = $19,200

 Mr Thompson could have paid up to $19,200 for a market study
and still come out ahead! Since it costs only $10,000, the survey is
indeed worthwhile!
69
EVSI = (EV with SI + cost) − (EV without SI)
EVSI = ($49,200 + $10,000) − $40,000 = $19,200
Thompson’s Complex Decision Tree

70
EVSI = expected value of sample information
EVPI = expected value of perfect information (see Slide 27)
Efficiency of Sample Information
• Possibly many types of sample information available

• Different sources can be evaluated
EVSI
Efficiency of sample information = 100%
EVPI
• For Thompson
19,200
Efficiency of sample information = 100% = 32%
60,000
Market survey is only 32% as efficient as perfect
information!
71
How sensitive are the decisions to changes in the

probabilities?
Thompson Lumber Example:

• How sensitive is our decision (to conduct the marketing
survey) to the probability of a favourable survey result?
• If the probability of a favourable result (p = .45) were to

change, would we make the same decision?
• How much could it change before we would make a

different decision?
72
p = probability of a favourable 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
$104,000p + $2,400 = $40,000
$104,000p = $37,600
p = $37,600÷$104,000 = 0.36
If p < 0.36, do not conduct the survey
If p > 0.36, conduct the survey
73
Thompson’s Complex Decision Tree

74
Bayesian Analysis
• Many ways of getting probability data

o Management’s experience and intuition
o Historical data
o Computed from other data using Bayes’ theorem
• Bayes’ theorem incorporates initial estimates and
information about the accuracy of the sources (e.g.
market research survey)
• Bayes’ theorem approach recognises that a decision maker
does not know with certainty what state of nature will
occur. It allows the manager to revise his/her prior
probability assessments based on new information
75
* Mr. Thompson’s best estimates of a favourable and
unfavourable market without any market survey information!
Calculating Revised Probabilities (1 of 9)
In the Thompson Lumber case we made the assumption

that the four conditional probabilities were known:
P(favourable market(FM) | survey results positive) = 0.78
P(unfavourable market(UM) | survey results positive) = 0.22
P(favourable market(FM) | survey results negative) = 0.27
P(unfavourable market(UM) | survey results negative) = 0.73
Prior probabilities*:
P(FM) = 0.50
P(UM) = 0.50
76
Let’s see how Mr. Thompson was able to derive these values with
Bayes’ theorem:
• From discussions with market research specialists, Mr. Thompson
knows that special surveys can either be positive (predict a
favourable market) or be negative (predict an unfavourable market).
• The experts have told Mr. Thompson that, statistically, of all new
products with a favourable market (FM), market surveys were
positive and predicted success correctly 70% of the time.
Thirty percent of the time the surveys falsely predicted
negative results or an unfavourable market (UM).
• When there was actually an unfavourable market for a new
product, 80% of the surveys correctly predicted negative
results. The surveys incorrectly predicted positive results the
remaining 20% of the time.
77
Market Survey Reliability in Predicting States of Nature:
They are an indication of the accuracy of the survey to

be conducted!
78
Let’s compute Thompson’s posterior probabilities:
• We need the probability of a favourable or unfavourable market

given a positive or negative result from the market study!
General form of Bayes’ theorem (see Chapter 2):
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 = unfavourable market
A = favourable market
B = positive survey
79
A’ = complement of A
B = positive survey
• 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 probability of a
positive survey
• 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
81
A’ = complement of A
B = negative survey
• 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 probability of a
negative survey
• 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
83
• The posterior probabilities now provide the Thompson

Lumber managers with estimates for each state of
nature if the survey results are positive or negative!
• Mr. Thompson’s prior probability of success without a

market survey was only 0.50.
• Now he is aware that the probability of successfully
marketing storage sheds will be 0.78 if his survey shows
positive results. His chances of success drop to 27% if
the survey report is negative!
86
Potential Problems Using Survey Results
• We can not always get the necessary data for analysis
• Survey results may be based only on those cases

where an action was taken
• Conditional probability information may not be as

accurate as we would like
87
Why do people make decisions that do not maximise their EMV?
Utility Theory (1 of 6)
• Monetary value is not always a true indicator of the

overall value of the result of a decision! There are
occasions in which people make decisions that would
appear to be inconsistent with the EMV criterion!
Example:
A manager may rule out one potential decision because it
could bankrupt the firm if things go bad, even though the
expected return for this decision is better than that of all
other alternatives!
88
Economists assume that rational people make decisions to
maximise their utility!
Why do people make decisions that do not maximise their

EMV?
• The monetary value is not always a true indicator of the
overall value of the result of the decision!
• The overall worth of a particular outcome is called
utility, and rational people make decisions that
maximise the expected utility!
• Although at times the monetary value is a good indicator
of utility, there are other times when it is not. This is
particularly true when some of the values involve an
extremely large payoff or an extremely large loss.
89
Example:
• 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.
90
How would you decide? $2 million for sure instead of a 50%
chance at nothing?
Your Decision Tree for the Lottery Ticket:

91
• Utility assessment assigns the worst outcome a utility

of 0 and the best outcome a utility of 1
• A standard gamble is used to determine utility values
• When you are indifferent, your utility values are equal

92
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
93
A utility curve is a graph that plots utility value versus monetary
value!
Investment Example (1 of 3)
• Mrs. Dickson would like to construct a utility curve revealing her

preference for money between $0 and $10,000.
• She can either invest her money in a bank savings account or she can
invest the same money in a real estate deal.
• If the money is invested in the bank, in three years Jane would have
$5,000.
• If she invested in the real estate, after three years she could either
have nothing ($0) or $10,000.
• Mrs. Dickson is very conservative. Unless there is an 80% chance of
getting $10,000 from the real estate deal, she would prefer to have her
money in the bank.
• What Mrs. Dickson has done here is to assess her utility for $5,000. When
there is an 80% chance (p = 0.8) of getting $10,000, she is indifferent
between putting her money in real estate or putting it in the bank. Her
utility for $5,000 is thus equal to 0.8, which is the same as the value for p.
94
Utility of $5,000
95
Let’s assess other utility values:

Utility for $7,000 = 0.90
Utility for $3,000 = 0.50
• Use the three different dollar amounts and assess

utilities
96
Risk avoider or risk seeker?
Utility Curve (1 of 2)
Utility Curve for Mrs. Dickson:

97
Utility Curve (2 of 2)
• Typical of a risk avoider

o Less utility from greater risk
o Avoids situations where high losses might occur
o As monetary value increases, utility curve increases at a slower
rate
• A risk seeker gets more utility from greater risk

o As monetary value increases, the utility curve increases at a
faster rate
• Someone who is indifferent will have a linear utility

curve
98
Utility as a Decision-Making Criteria (1 of 5)
• After a utility curve has been determined, the utility

values from the curve are used in making decisions.
• Monetary outcomes or values are replaced with the

appropriate utility values and then decision analysis
is performed as usual.
• The expected utility for each alternative is computed

instead of the EMV.
99
• Mr. Simkin loves to gamble. He decides to play a game

that involves tossing thumbtacks in the air.
o If the thumbtack lands point up, he wins $10,000
o If the thumbtack lands point down, he loses $10,000
o Mr. Simkin believes that there is a 45% chance of
winning $10,000 and a 55% chance of suffering the
$10,000 loss. Alternative 2 is not to gamble.
• Should Mr. Simkin play the game (alternative 1) or

should he not play the game (alternative 2)?
100
EMV (play game) = (0.45)($10,000) + (0.55)(−$10,000) = -$1,000
EMV (don’t play game) = 0
Decision Facing Mr. Simkin:

101
He has a total of $20,000 to gamble, so he has constructed the utility curve
based on a best payoff of $20,000 and a worst payoff of a $20,000 loss.
Step 1 – Define Mr. Simkin’s utilities:

U(−$10,000) = 0.05
U($0) = 0.15
U($10,000) = 0.30
Utility Curve for Mr. Simkin

102
Step 2 – Replace monetary values with utility values
E(alternative 1: play the game) =(0.45)(0.30) + (0.55)(0.05)

= 0.135 + 0.027 = 0.162
E(alternative 2: don’t play the game) = 0.15

103
• Alternative 1 is the best strategy using utility as the

decision criterion.
• If EMV had been used, alternative 2 would have been
the best strategy.
• The utility curve is a risk-seeker utility curve, and the
choice of playing the game certainly reflects this
preference for risk!
104
Homework --- Chapter 3
• End of chapter self-test 1-16

(pp. 115-116)
• Discussion Questions and
Problems 3.30 and 3.31
Compile all answers into one
document and submit at the
beginning of the next lecture!
On the top of the document,
write your Pinyin-Name and
Student ID.
• Please read Chapter 4!
105
Case Study (1 of 8)
‘Starting Right Corporation’ (p. 125)

After watching a movie about a young woman who quit a
successful corporate career to start her own baby food
company, Julia Day decided that she wanted to do the
same. In the movie, the babyfood company was very
successful. Julia knew, however, that it is much easier to
make a movie about a successful woman starting her own
company than to actually do it. The product had to be of
the highest quality, and Julia had to get the best people
involved to launch the new company. Julia resigned from
her job and launched her new company – “Starting Right”.
106
Case Study (2 of 8)
Julia decided to target the upper end of the baby food

market by producing baby food that contained no
preservatives but had a great taste. Although the price
would be slightly higher than for existing baby food, Julia
believed that parents would be willing to pay more for a
high-quality baby food. Instead of putting baby food in jars,
which would require preservatives to stabilise the food,
Julia decided to try a new approach. The baby food
would be frozen. This would allow for natural ingredients,
no preservatives, and outstanding nutrition.
107
Case Study (3 of 8)
Getting good people to work for the new company was

also important. Julia decided to find people with
experience in finance, marketing, and production to get
involved with Starting Right. With her enthusiasm and
charisma, Julia was able to find such a group. Their first
step was to develop prototypes of the new frozen baby
food and to perform a small pilot test of the new product.
The pilot test received rave reviews.
108
Case Study (4 of 8)
The final key to getting the young company off to a good

start was to raise funds. Three options were considered:
corporate bonds, preferred stock, and common stock. Julia
decided that each investment should be in blocks of
$30,000. Furthermore, each investor should have an
annual income of at least $40,000 and a net worth of
$100,000 to be eligible to invest in Starting Right.
Corporate bonds would return 13% per year for the next 5
years. Julia furthermore guaranteed that investors in the
corporate bonds would get at least $20,000 back at the
end of five years. Investors in preferred stock should see
their initial investment increase by a factor of 4 with a good
109
Case Study (5 of 8)
market or see the investment worth only half of the initial

investment with an unfavourable market. The common
stock had the greatest potential. The initial investment was
expected to increase by a factor of 8 with a good market,
but investors would lose everything if the market was
unfavourable.
110
Case Study (6 of 8)
Discussion Questions
1. Sue Pansky, a retired elementary school teacher, is
considering investing in Starting Right. She is very
conservative and is a risk avoider. What do you
recommend?
2. Ray Cahn, who is currently a commodities broker, is
also considering an investment, although he believes
that there is only an 11% chance of success. What do
you recommend?
111
Case Study (7 of 8)
3. Lila Battle has decided to invest in Starting Right. While
she believes that Julia has a good chance of being
successful, Lila is a risk avoider and very
conservative. What is your advice to Lila?
4. George Yates believes that there is an equally likely
chance for success. What is your recommendation?
5. Peter Metarko is extremely optimistic about the
market for the new baby food. What is your advice for
Pete?
112
Case Study (8 of 8)
6. Julia Day has been told that developing the legal
documents for each fundraising alternative is
expensive. Julia would like to offer alternatives for both
risk-averse and risk-seeking investors. Can Julia
delete one of the financial alternatives and still
offer investment choices for risk seekers and risk
avoiders?
113
Solution – Case Study (1 of 6)
• This is a decision-making-under-uncertainty case.
• There are two events: a favourable market (event 1)

and an unfavourable market (event 2).
• There are four alternatives, which include do nothing

(alternative 1), invest in corporate bonds (alternative 2),
invest in preferred stock (alternative 3), and invest in
common stock (alternative 4).
114
Compound interest!
Decision table:
STATE OF NATURE
ALTERNATIVE Event 1 Event 2
Favourable Unfavourable
Market Market
Alternative 1 (do nothing) 0 0
Alternative 2 (corporate bonds) 55,273 -10,000
Alternative 3 (preferred stock) 120,000 -15,000
Alternative 4 (common stock) 240,000 -30,000
• For alternative 2, the return in a good market is $30,000 (1 + 0.13)5

= $55,273. The return in a good market is $120,000, (4 x $30,000)
for alternative 3, and $240,000, (8 x $30,000) for alternative 4.
115
Decision Table:
STATE OF NATURE
ALTERNATIVE Event 1 Event 2 Laplace Minimum Maxi- Hurwicz

Favourable Unfavourable Average mum Value
Market Market Value
Alternative 1 0 0 0.0 0 0 0.00
(do nothing)
Alternative 2 55,273 -10,000 22,636.5 -10,000 55,273 -2,819.97
(corporate bonds)
Alternative 3 120,000 -15,000 52,500.0 -15,000 120,000 -150.00
(preferred stock)
Alternative 4 240,000 -30,000 105,000.0 -30,000 240,000 -300.00
(common stock)
116
Regret Table:
STATE OF NATURE
ALTERNATIVE Event 1 Event 2 Maximum Regret

Favourable Unfavourable
Market Market
Alternative 1 0 0 240,000
(do nothing)
Alternative 2 55,273 -10,000 184,727
(corporate bonds)
Alternative 3 120,000 -15,000 120,000
(preferred stock)
Alternative 4 240,000 -30,000 30,000
(common stock)
117
• Sue Pansky is a risk avoider and should use the maximin

decision approach. She should do nothing and not make an
investment in Starting Right!
• Ray Cahn should use a coefficient of realism of 0.11. The best

decision is to do nothing.
• Lila Battle should eliminate alternative 1 of doing nothing and

apply the maximin criterion. The result is to invest in the
corporate bonds.
118
• George Yates should use the equally likely decision criterion.

The best decision for George is to invest in common stock.
• Pete Metarko is a risk seeker. He should invest in common stock.
• Julia Day can eliminate the preferred stock alternative and still
offer alternatives to risk seekers (common stock) and risk
avoiders (doing nothing or investing in corporate bonds).

Decision Analysis: Optimize Your Decision-Making

Hochgeladen von

Dokumentinformationen

Originalbeschreibung:

Originaltitel

Copyright

Verfügbare Formate

Dieses Dokument teilen

Dokument teilen oder einbetten

Freigabeoptionen

Stufen Sie dieses Dokument als nützlich ein?

Sind diese Inhalte unangemessen?

Copyright:

Verfügbare Formate

Decision Analysis: Optimize Your Decision-Making

Hochgeladen von

Copyright:

Verfügbare Formate

1

Textbook: pp. 81-128

Chapter 3: Decision Analysis

After completing this chapter, students will be able to:

• What is involved in making a good decision?

• Decision theory is an analytic and systematic

• A good decision is one that is based on logic,

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

4. List the payoff (typically profit) of each

5. Select one of the mathematical decision theory

6. Apply the model and make your decision

Thompson Lumber Company (1 of 3)

Step 1 – Define the problem

Step 2 – List alternatives

Step 3 – Identify possible outcomes, states of nature

Thompson Lumber Company (2 of 3)

Step 4 – List the payoffs

Step 5 – Select the decision model

Step 6 – Apply the model to the data

Thompson Lumber Company (3 of 3)

Decision Table with Conditional Values for Thompson

Note: It is important to include all alternatives, including

Types of Decision-Making Environments

• Decision making under certainty

• Decision making under uncertainty

• Decision making under risk

Decision Making Under Uncertainty

Several states of nature exist and a manager cannot

• Used to find the alternative that maximises the

• Used to find the alternative that maximises the minimum

Criterion of Realism (Hurwicz) (1 of 2)

• Often called weighted average

The advantage of this approach is that it

• Select a coefficient of realism α, with 0 ≤ α ≤ 1

• Select the alternative with the highest value

Weighted average = α(best in row) + (1−α)(worst in row)

Criterion of Realism (Hurwicz) (2 of 2)

For the large plant alternative using α = 0.8

Equally Likely (Laplace)

• Considers all the payoffs for each alternative

Thompson’s Equally Likely Decision: 200,000 * 0.5 +

• Based on opportunity loss or regret

1. Create an opportunity loss table by determining the

2. Calculate opportunity loss by subtracting each payoff in

3. Find the maximum opportunity loss for each alternative

Determining Opportunity Losses for Thompson Lumber:

Opportunity Loss Table for Thompson Lumber:

Thompson’s Minimax Decision Using Opportunity Loss:

Decision Making Under Risk (1 of 2)

EMV  alternative  =  X i P  X i 

Decision Making Under Risk (2 of 2)

Expanding the equation:

EMV  alternative  =  X i P  X i 

EMV for Thompson Lumber (1 of 2)

EMV (large plant) = ($200,000)(0.5) + (−$180,000)(0.5)

EMV (small plant) = ($100,000)(0.5) + (−$20,000)(0.5)

EMV (do nothing) = ($0)(0.5) + ($0)(0.5)

EMV for Thompson Lumber (2 of 2)

Decision Table with Probabilities and EMVs for Thompson

EVwPI = $7000.4 + $1,0000,3 + $1,150*0.3 = $925