Valua%on

and pricing
(November 5, 2013) LEARNING OBJECTIVES
Lecture 4
Decision making
(part 1) 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
10/8/16, 2:46 AM

decision making.
Olivier J. de Jong, LL.M., MM., MBA, CFD, CFFA, AA
www.olivierdejong.com Copyright ©2015 Pearson Education, Inc. 3–2

The Six Steps in

Introduction
https://targetcareers.co.uk/sites/targetcareers.co.uk/files/public/Bangor.jpg Page 1 of 1
Decision Making
•  What is involved in making a good decision?
•  Decision theory is an analytic and systematic 1.  Clearly define the problem at hand
approach to the study of decision making 2.  List the possible alternatives
•  A good decision is one that is based on logic, 3.  Identify the possible outcomes or states of
considers all available data and possible nature
alternatives, and applies a quantitative 4.  List the payoff (typically profit) of each
approach combination of alternatives and outcomes
5.  Select one of the mathematical decision
theory models
6.  Apply the model and make your decision

Copyright ©2015 Pearson Education, Inc. 3–3 Copyright ©2015 Pearson Education, Inc. 3–4

Thompson Lumber Company Thompson Lumber Company

Step 1 – Define the problem
•  Consider expanding by manufacturing Step 4 – List the payoffs
and marketing a new product – backyard •  Identify conditional values for the profits
storage sheds for large plant, small plant, and no
Step 2 – List alternatives development for the two possible market
conditions
•  Construct a large new plant
Step 5 – Select the decision model
•  Construct a small new plant
•  Depends on the environment and
•  Do not develop the new product line
amount of risk and uncertainty
Step 3 – Identify possible outcomes, states of Step 6 – Apply the model to the data
nature
•  The market could be favorable or
unfavorable
Copyright ©2015 Pearson Education, Inc. 3–5 Copyright ©2015 Pearson Educa%on, Inc. 3–6
 Types of Decision-Making
Thompson Lumber Company
Environments
TABLE 3.1 – Conditional Values •  Decision making under certainty
–  The decision maker knows with certainty the
STATE OF NATURE consequences of every alternative or decision
choice
FAVORABLE UNFAVORABLE
ALTERNATIVE MARKET ($) MARKET ($) •  Decision making under uncertainty
Construct a large plant 200,000 –180,000 –  The decision maker does not know the
probabilities of the various outcomes
Construct a small plant 100,000 –20,000
•  Decision making under risk
Do nothing 0 0 –  The decision maker knows the probabilities of the
various outcomes

Copyright ©2015 Pearson Educa%on, Inc. 3–7 Copyright ©2015 Pearson Education, Inc. 3–8

Decision Making Under

Uncertainty Optimistic
•  Used to find the alternative that maximizes the
•  Criteria for making decisions under maximum payoff – maximax criterion
uncertainty –  Locate the maximum payoff for each alternative
–  Select the alternative with the maximum number
1.  Maximax (optimistic)
2.  Maximin (pessimistic) TABLE 3.2 – Thompson’s Maximax Decision

3.  Criterion of realism (Hurwicz) STATE OF NATURE

4.  Equally likely (Laplace) FAVORABLE UNFAVORABLE MAXIMUM IN
ALTERNATIVE MARKET ($) MARKET ($) A ROW ($)
5.  Minimax regret
Construct a large plant 200,000 –180,000 200,000
Construct a small plant 100,000 –20,000 100,000
Maximax
Do nothing 0 0 0

Copyright ©2015 Pearson Education, Inc. 3–9 Copyright ©2015 Pearson Education, Inc. 3 – 10

Pessimistic Criterion of Realism (Hurwicz)

•  Used to find the alternative that maximizes the •  Often called weighted average
minimum payoff – maximin criterion –  Compromise between optimism and pessimism
–  Locate the minimum payoff for each alternative
–  Select a coefficient of realism α, with 0 ≤ α ≤ 1
–  Select the alternative with the maximum number
α = 1 is perfectly optimistic
TABLE 3.3 – Thompson’s Maximin Decision α = 0 is perfectly pessimistic
STATE OF NATURE –  Compute the weighted averages for each
alternative
FAVORABLE UNFAVORABLE MINIMUM IN
ALTERNATIVE MARKET ($) MARKET ($) A ROW ($) –  Select the alternative with the highest value
Construct a large plant 200,000 –180,000 –180,000
Construct a small plant 100,000 –20,000 –20,000
Weighted average = α(best in row)
+ (1 – α)(worst in row)
Do nothing 0 0 0
Maximin
Copyright ©2015 Pearson Education, Inc. 3 – 11 Copyright ©2015 Pearson Education, Inc. 3 – 12
Criterion of Realism (Hurwicz) Equally Likely (Laplace)
For the large plant alternative using α = 0.8
•  Considers all the payoffs for each alternative
(0.8)(200,000) + (1 – 0.8)(–180,000) = 124,000 –  Find the average payoff for each alternative
For the small plant alternative using α = 0.8 –  Select the alternative with the highest average
(0.8)(100,000) + (1 – 0.8)(–20,000) = 76,000
TABLE 3.5 – Thompson’s Equally Likely Decision
TABLE 3.4 – Thompson’s Criterion of Realism Decision

STATE OF NATURE STATE OF NATURE

CRITERION FAVORABLE UNFAVORABLE ROW
FAVORABLE UNFAVORABLE OF REALISM ALTERNATIVE MARKET ($) MARKET ($) AVERAGE ($)
ALTERNATIVE MARKET ($) MARKET ($) (α = 0.8) $
Construct a large plant 200,000 –180,000 10,000
Construct a large plant 200,000 –180,000 124,000
Realism Construct a small plant 100,000 –20,000 40,000
Construct a small plant 100,000 –20,000 76,000 Equally likely
Do nothing 0 0 0
Do nothing 0 0 0

Copyright ©2015 Pearson Education, Inc. 3 – 13 Copyright ©2015 Pearson Education, Inc. 3 – 14

Minimax Regret Minimax Regret

•  Based on opportunity loss or regret TABLE 3.6 – Determining Opportunity Losses for Thompson Lumber

–  The difference between the optimal profit and

actual payoff for a decision STATE OF NATURE

1.  Create an opportunity loss table by determining FAVORABLE UNFAVORABLE

the opportunity loss from not choosing the best MARKET MARKET
alternative ($) ($)

2.  Calculate opportunity loss by subtracting each 200,000 – 200,000 0 – (–180,000)

payoff in the column from the best payoff in the
column 200,000 – 100,000 0 – (–20,000)
3.  Find the maximum opportunity loss for each
alternative and pick the alternative with the 200,000 – 0 0–0
minimum number

Copyright ©2015 Pearson Educa%on, Inc. 3 – 15 Copyright ©2015 Pearson Educa%on, Inc. 3 – 16

Minimax Regret Minimax Regret

TABLE 3.7 – Opportunity Loss Table for Thompson Lumber
TABLE 3.8 – Thompson’s Minimax Decision Using Opportunity Loss

STATE OF NATURE
STATE OF NATURE
FAVORABLE UNFAVORABLE FAVORABLE UNFAVORABLE MAXIMUM IN
ALTERNATIVE MARKET ($) MARKET ($) ALTERNATIVE MARKET ($) MARKET ($) A ROW ($)
Construct a large
Construct a large plant 0 180,000 0 180,000 180,000
plant
Construct a small plant 100,000 20,000 Construct a small
100,000 20,000 100,000
plant
Minimax
Do nothing 200,000 0 Do nothing 200,000 0 200,000

Copyright ©2015 Pearson Educa%on, Inc. 3 – 17 Copyright ©2015 Pearson Educa%on, Inc. 3 – 18
 Decision Making Under Risk Decision Making Under Risk
•  When there are several possible states of
nature and the probabilities associated with •  Expanding the equation
each possible state are known
–  Most popular method – choose the alternative with EMV (alternative i) = (payoff of first state of nature)
the highest expected monetary value (EMV) x (probability of first state of nature)
+ (payoff of second state of nature)
EMV(alternative) = ∑ X P(X )
i i x (probability of second state of nature)
+ … + (payoff of last state of nature)
where
x (probability of last state of nature)
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

Copyright ©2015 Pearson Educa%on, Inc. 3 – 19 Copyright ©2015 Pearson Educa%on, Inc. 3 – 20

EMV for Thompson Lumber EMV for Thompson Lumber

•  Each market outcome has a probability of TABLE 3.9 – Decision Table with Probabilities and EMVs
occurrence of 0.50 STATE OF NATURE
•  Which alternative would give the highest FAVORABLE UNFAVORABLE
ALTERNATIVE MARKET ($) MARKET ($) EMV ($)
EMV?
Construct a large plant 200,000 –180,000 10,000
EMV (large plant) = ($200,000)(0.5) + (–$180,000)(0.5)
Construct a small plant 100,000 –20,000 40,000
= $10,000
EMV (small plant) = ($100,000)(0.5) + (–$20,000)(0.5) Do nothing 0 0 0

= $40,000 Probabilities 0.50 0.50 Best EMV

EMV (do nothing) = ($0)(0.5) + ($0)(0.5)
= $0
Copyright ©2015 Pearson Educa%on, Inc. 3 – 21 Copyright ©2015 Pearson Educa%on, Inc. 3 – 22

Expected Value of Perfect Expected Value of Perfect

Information (EVPI) Information (EVPI)
•  EVPI places an upper bound on what you •  Expanded EVwPI becomes
should pay for additional information
•  EVwPI is the long run average return if we EVwPI = (best payoff for first state of nature)
x (probability of first state of nature)
have perfect information before a decision is
+ (best payoff for second state of nature)
made
x (probability of second state of nature)
+ … + (best payoff for last state of nature)
EVwPI = ∑(best payoff in state of nature i)
x (probability of last state of nature)
(probability of state of nature i)
•  And
EVPI = EVwPI – Best EMV

Copyright ©2015 Pearson Education, Inc. 3 – 23 Copyright ©2015 Pearson Education, Inc. 3 – 24
 Expected Value of Perfect Expected Value of Perfect
Information (EVPI) Information (EVPI)
TABLE 3.10 – Decision Table with Perfect Information
•  Scientific Marketing, Inc. offers analysis that
will provide certainty about market conditions STATE OF NATURE

(favorable) ALTERNATIVE
FAVORABLE
MARKET ($)
UNFAVORABLE
MARKET ($) EMV ($)
•  Additional information will cost $65,000 Construct a large plant 200,000 -180,000 10,000
•  Should Thompson Lumber purchase the
information? Construct a small plant 100,000 -20,000 40,000

Do nothing 0 0 0
With perfect
200,000 0 100,000
information
EVwPI
Probabilities 0.5 0.5

Copyright ©2015 Pearson Education, Inc. 3 – 25 Copyright ©2015 Pearson Education, Inc. 3 – 26

Expected Value of Perfect Expected Value of Perfect

Information (EVPI) Information (EVPI)
•  The maximum EMV without additional •  The maximum EMV without additional
information is $40,000 information is $40,000
Thompson should not pay
–  Therefore –  Therefore $65,000 for this information

EVPI = EVwPI – Maximum EMV EVPI = EVwPI – Maximum EMV

= $100,000 - $40,000 = $100,000 - $40,000
= $60,000 = $60,000

So the maximum Thompson should pay So the maximum Thompson should pay
for the additional information is $60,000 for the additional information is $60,000

Copyright ©2015 Pearson Education, Inc. 3 – 27 Copyright ©2015 Pearson Education, Inc. 3 – 28

Expected Opportunity Loss Expected Opportunity Loss

EOL (large plant) = (0.50)($0) + (0.50)($180,000) = $90,000
•  Expected opportunity loss (EOL) is the cost of
EOL (small plant) = (0.50)($100,000) + (0.50)($20,000) = $60,000
not picking the best solution
–  Construct an opportunity loss table EOL (do nothing) = (0.50)($200,000) + (0.50)($0) = $100,000

–  For each alternative, multiply the opportunity loss TABLE 3.11 – EOL Table for Thompson Lumber
by the probability of that loss for each possible STATE OF NATURE
outcome and add these together FAVORABLE UNFAVORABLE
–  Minimum EOL will always result in the same ALTERNATIVE MARKET ($) MARKET ($) EOL
decision as maximum EMV Construct a large plant 0 180,000 90,000
–  Minimum EOL will always equal EVPI Construct a small plant 100,000 20,000 60,000
Do nothing 200,000 0 100,000
Best EOL
Probabilities 0.5 0.5

Copyright ©2015 Pearson Education, Inc. 3 – 29 Copyright ©2015 Pearson Education, Inc. 3 – 30
 Sensitivity Analysis Sensitivity Analysis
FIGURE 3.1

EMV(large plant) = $200,000P – $180,000)(1 – P)

EMV Values
= $200,000P – $180,000 + $180,000P
= $380,000P – $180,000 $300,000

$200,000 EMV (large plant)

Point 2
EMV(small plant) = $100,000P – $20,000)(1 – P)
= $100,000P – $20,000 + $20,000P $100,000 Point 1 EMV (small plant)

= $120,000P – $20,000
0 EMV (do nothing)
.167 .615 1
EMV(do nothing) = $0P + 0(1 – P) –$100,000 Values of P
= $0
–$200,000

Copyright ©2015 Pearson Education, Inc. 3 – 31 Copyright ©2015 Pearson Education, Inc. 3 – 32

Sensitivity Analysis Sensitivity Analysis

RANGE OF
Point 1: EMV(do nothing) = EMV(small plant) BEST ALTERNATIVE P VALUES
Do nothing Less than 0.167
20,000
0 = $120,000P − $20,000 P= = 0.167 Construct a small plant 0.167 – 0.615
120,000 FIGURE 3.1

EMV Values Construct a large plant Greater than 0.615

$300,000

Point 2: EMV(small plant) = EMV(large plant) $200,000 Point 2 EMV (large plant)

$100,000 Point 1
$120,000P − $20,000 = $380,000P − $180,000 EMV (small plant)

0 EMV (do nothing)

160,000
P= = 0.615 –$100,000
.167 .615 1
260,000 Values of P

–$200,000

Copyright ©2015 Pearson Education, Inc. 3 – 33 Copyright ©2015 Pearson Education, Inc. 3 – 34

A Minimization Example A Minimization Example

•  Three year lease for a copy machine •  Three year lease for a copy machine
–  Which machine should be selected? –  Which machine should be selected?

TABLE 3.12 – Payoff Table TABLE 3.13 – Best and Worst Payoffs

10,000 20,000 30,000

10,000 COPIES 20,000 COPIES 30,000 COPIES COPIES COPIES COPIES
BEST WORST
PER MONTH PER MONTH PER MONTH PAYOFF PAYOFF
PER PER PER
(MINIMUM) (MAXIMUM)
MONTH MONTH MONTH
Machine A 950 1,050 1,150
Machine A 950 1,050 1,150 950 1,150
Machine B 850 1,100 1,350
Machine B 850 1,100 1,350 850 1,350
Machine C 700 1,000 1,300
Machine C 700 1,000 1,300 700 1,300

Copyright ©2015 Pearson Education, Inc. 3 – 35 Copyright ©2015 Pearson Education, Inc. 3 – 36
 A Minimization Example A Minimization Example
•  Using Hurwicz criteria with 70% coefficient •  For equally likely criteria

Weighted average = 0.7(best payoff)

+ (1 – 0.7)(worst payoff) For each machine
Machine A: (950 + 1,050 + 1,150)/3 = 1,050
For each machine Machine B: (850 + 1,100 + 1,350)/3 = 1,100
Machine A: 0.7(950) + 0.3(1,150) = 1,010 Machine C: (700 + 1,000 + 1,300)/3 = 1,000
Machine B: 0.7(850) + 0.3(1,350) = 1,000
Machine C: 0.7(700) + 0.3(1,300) = 880

Copyright ©2015 Pearson Education, Inc. 3 – 37 Copyright ©2015 Pearson Education, Inc. 3 – 38

A Minimization Example A Minimization Example

•  For EMV criteria •  For EMV criteria
TABLE 3.14 – Expected Monetary Values and Expected Value with Perfect Information

10,000 20,000 30,000

USAGE PROBABILITY COPIES COPIES COPIES
PER PER PER EMV
10,000 0.40
MONTH MONTH MONTH
20,000 0.30
Machine A 950 1,050 1,150 1,040
30,000 0.30
Machine B 850 1,100 1,350 1,075

Machine C 700 1,000 1,300 970

With perfect information 700 1,000 1,150 925

Probability 0.4 0.3 0.3

Copyright ©2015 Pearson Education, Inc. 3 – 39 Copyright ©2015 Pearson Education, Inc. 3 – 40

A Minimization Example A Minimization Example

•  For EVPI •  Opportunity loss criteria
TABLE 3.15 – Expected Monetary Values and Expected Value with Perfect Information
EVwPI = $925
TABLE 3.15 – Opportunity Loss Table
10,000 20,000 30,000
Best EMV without perfect
COPIESinformation
COPIES = $970
COPIES
EMV 10,000 20,000 30,000
PER PER
EVPI = 970 – 925 = $45 PER COPIES COPIES COPIES
MONTH MONTH MONTH PER PER PER
MONTH MONTH MONTH MAXIMUM EOL
Machine A 950 1,050 1,150 1,040
Machine A 250 50 0 250 115
Machine B 850 1,100 1,350 1,075
Machine B 150 100 200 200 150
Machine C 700 1,000 1,300 970
Machine C 0 0 150 150 45
With perfect information 700 1,000 1,150 925
Probability 0.4 0.3 0.3
Probability 0.4 0.3 0.3

Copyright ©2015 Pearson Education, Inc. 3 – 41 Copyright ©2015 Pearson Education, Inc. 3 – 42
 Remember
Chapter 3: Where Prices Come From: The Interaction of Demand and Supply

¡  Read Quantitative Methods-module guide.

¡  Any questions please e-mail: [email protected]

¡  … and make notes as you do so, in whatever way works best for you
in terms of remembering information (your performance on this
course is only assessed by exam).

Copyright © 2010 Pearson Education, Inc. · Economics · R. Glenn Hubbard, Anthony Patrick O’Brien, 3e. 43 of 46