Derek Poon

ELM Graduate School

(slides adapted from Russel & Taylor – Operations and Supply Chain Management, 8ed)
Decision Analysis
The Decision Process in Operations
1. Clearly define the problem and the factors
that influence it
2. Develop specific and measurable objectives
3. Develop a model
4. Evaluate each alternative solution
5. Select the best alternative
6. Implement the decision and set a timetable
for completion
Decision Analysis
Decision Analysis

Decision Analysis
A set of quantitative decision-making
techniques for decision situations in which
uncertainty exists

States of Nature
 Events that may occur in the future
Decision Analysis
Decision-Making Environments

 Decision making under uncertainty

Complete uncertainty as to which state of
nature may occur

 Decision making under risk

Several states of nature may occur
Each has a probability of occurring

 Decision making under certainty

State of nature is known
Decision Analysis
Payoff Table
Payoff table
 method for organizing and illustrating
payoffs from different decisions given
various states of nature
Payoff
 outcome of a decision
States Of Nature
Decision a b
1 Payoff 1a Payoff 1b
2 Payoff 2a Payoff 2b
Decision Analysis
Decision Making Criteria Under Uncertainty

Maximax
choose decision with the maximum of the
maximum payoffs – best of best case
Maximin
choose decision with the maximum of the
minimum payoffs – best of worst case
Minimax regret
 choose decision with the minimum of the
maximum regrets for each alternative –
lowest impact from error
Decision Analysis
Decision Making Criteria Under Uncertainty
Hurwicz
 choose decision in which decision payoffs
are weighted by a coefficient of optimism,
alpha (α)
 coefficient of optimism is a measure of a
decision maker’s optimism, from 0
(completely pessimistic) to 1 (completely
optimistic)
Equal likelihood (La Place)
 choose decision in which each state
of nature is weighted equally
Decision Analysis
Southern Textile Company
The Southern Textile Company is contemplating the future of one of its plants
located in South Carolina. Three alternative decisions are being considered:
(1) Expand the plant and produce lightweight, durable materials for possible
sale to the military, a market with little foreign competition;
(2) maintain the status quo at the plant, continuing production of textile goods
that are subject to heavy foreign competition; or
(3) sell the plant now. If one of the first two alternatives is chosen, the plant will
still be sold at the end of the year. The amount of profit that could be earned by
selling the plant in a year depends on foreign market conditions, including the
status of a trade embargo bill in Congress. The following payoff table describes
this decision situation.

STATES OF NATURE
Good Foreign Poor Foreign
DECISION Competitive Conditions Competitive Conditions
Expand $ 800,000 $ 500,000
Maintain status quo 1,300,000 -150,000
Sell now 320,000 320,000
Decision Analysis
Southern Textile Company
Determine the best decision using each of
the decision criteria.
1. Maximax
2. Maximin
3. Minimax regret
4. Hurwicz
5. Equal likelihood
Decision Analysis
Maximax Solution
(best of best case)
 Find the alternative that maximizes the
maximum outcome for every alternative
 Pick the outcome with the maximum number
 Highest possible gain
 This is viewed as an optimistic decision
criteria
Decision Analysis
Maximax Solution
(best of best case)
STATES OF NATURE
Good Foreign Poor Foreign
DECISION Competitive Conditions Competitive Conditions
Expand $ 800,000 $ 500,000
Maintain status quo 1,300,000 -150,000
Sell now 320,000 320,000

Expand: $800,000
Status quo: 1,300,000  Maximum
Sell: 320,000
Decision: Maintain status quo
Decision Analysis
Maximin Solution
(best of worst case)
 Find the alternative that maximizes the
minimum outcome for every alternative
 Pick the outcome with the minimum number
 Least possible loss
 This is viewed as a pessimistic decision
criteria
Decision Analysis
Maximin Solution
(best of worst case)
STATES OF NATURE
Good Foreign Poor Foreign
DECISION Competitive Conditions Competitive Conditions
Expand $ 800,000 $ 500,000
Maintain status quo 1,300,000 -150,000
Sell now 320,000 320,000

Expand: $500,000  Maximum

Status quo: -150,000
Sell: 320,000
Decision: Expand
Decision Analysis
Application in cost and profit conditions

Best of Best of
Best Approach Worst Approach
Maximax Maximin
Profit (Highest of the Highest) (Highest of the Lowest)

Minimin Minimax
Cost (Lowest of the Lowest) (Lowest of the Highest)
Decision Analysis
Minimax Regret Solution

 Regret – Loss against best case

 Calculate the regret for every case in each
state of nature
 For each case, pick the maximum regret
 Pick the situation with smallest maximum
regret
Decision Analysis
Minimax Regret Solution

States of Nature
Good Foreign Poor Foreign
Competitive Conditions Competitive Conditions

$1,300,000 - 800,000 = 500,000 $500,000 - 500,000 = 0

1,300,000 - 1,300,000 = 0 500,000 - (-150,000)= 650,000
1,300,000 - 320,000 = 980,000 500,000 - 320,000= 180,000

Expand: $500,000  Minimum

Status quo: 650,000
Sell: 980,000
Decision: Expand
Decision Analysis
Hurwicz Solution

 Alpha, α – Coefficient of optimism

 For each case, calculate Hurwicz payoff
value for
α x best state of nature +
(1 - α) x worst state of nature
 Pick the case with the best calculated
Hurwicz payoff value
Decision Analysis
Hurwicz Solution
STATES OF NATURE
Good Foreign Poor Foreign
DECISION Competitive Conditions Competitive Conditions
Expand $ 800,000 $ 500,000
Maintain status quo 1,300,000 -150,000
Sell now 320,000 320,000

 = 0.3 1 -  = 0.7

Expand: $800,000(0.3) + 500,000(0.7) = $590,000  Maximum

Status quo: 1,300,000(0.3) -150,000(0.7) = 285,000
Sell: 320,000(0.3) + 320,000(0.7) = 320,000
Decision: Expand
Decision Analysis
Equal Likelihood Solution

 For each case, calculate average payoff

value for all states of nature
 Pick the case with the best calculated
average payoff value
Decision Analysis
Equal Likelihood Solution

STATES OF NATURE
Good Foreign Poor Foreign
DECISION Competitive Conditions Competitive Conditions
Expand $ 800,000 $ 500,000
Maintain status quo 1,300,000 -150,000
Sell now 320,000 320,000

Two states of nature each weighted 0.50

Expand: $800,000(0.5) + 500,000(0.5) = $650,000  Maximum
Status quo: 1,300,000(0.5) -150,000(0.5) = 575,000
Sell: 320,000(0.5) + 320,000(0.5) = 320,000
Decision: Expand
Decision Analysis
A-15
The director of career advising at Grand Valley Community College wants to
use decision analysis to provide information to help students decide which
two-year degree program they should pursue. The director has set up the
following payoff table for six of the most popular and successful degree
programs at GVCC that shows the estimated five-year gross income ($) from
each degree for four future economic conditions:
Economic Conditions
Degree Program Recession Average Good Robust
Graphic Design 115,000 155,000 190,000 220,000
Nursing 140,000 175,000 210,000 225,000
Real Estate 95,000 135,000 230,000 350,000
Medical Technology 120,000 180,000 210,000 270,000
Culinary Technology 85,000 125,000 180,000 290,000
Computer Information Techonology 125,000 160,000 200,000 260,000
Determine the best degree program in terms of projected income,
using the following decision criteria:
a. Maximax
b. Maximin
c. Minimax Regret
d. Hurwicz (α = 0.3)
d. Equal likelihood
Decision Analysis
A-15
a. Maximax
Graphic Design 220,000
Nursing 225,000
Real Estate 350,000 Maximum
Medical Technology 270,000
Culinary Technoloy 290,000
Computer Information Technology 260,000
Select Real Estate

b. Maximin
Graphic Design 115,000
Nursing 140,000 Maximum
Real Estate 95,000
Medical Technology 120,000
Culinary Technoloy 85,000
Computer Information Technology 125,000
Select Nursing
Decision Analysis
A-15
c. Minimax Regret
Regret
Maximum
Degree Program Recession Average Good Robust Regret
Graphic Design 140,000-115,000 180,000-155,000 230,000-190,000 350,000-220,000 130,000
= 25,000 = 25,000 = 40,000 =130,000
Nursing 140,000-140,000 180,000-175,000 230,000-210,000 350,000-225,000 125,000
= 0 = 5,000 = 20,000 =125,000
Real Estate 140,000- 95,000 180,000-135,000 230,000-230,000 350,000-350,000 45,000 <-Minimum
= 45,000 = 45,000 = 0 = 0
Medical Technology 140,000-120,000 180,000-180,000 230,000-210,000 350,000-270,000 80,000
= 20,000 = 0 = 20,000 = 80,000
Culinary Technology 140,000- 85,000 180,000-125,000 230,000-180,000 350,000-290,000 60,000
= 55,000 = 55,000 = 50,000 = 60,000
Computer Information 140,000-125,000 180,000-160,000 230,000-200,000 350,000-260,000 90,000
Techonology = 15,000 = 20,000 = 30,000 =90,000

Select Real Estate

d. Hurwicz (α=0.3)
Graphic Design 0.3(220,000)+(1-0.3)(115,000)=146,000
Nursing 0.3(225,000)+(1-0.3)(140,000)=165,500
Real Estate 0.3(350,000)+(1-0.3)( 95,000)=171,500<-Maximum
Medical Technology 0.3(270,000)+(1-0.3)(120,000)=165,000
Culinary Technoloy 0.3(290,000)+(1-0.3)( 85,000)=146,500
Computer Information Technology 0.3(260,000)+(1-0.3)(125,000)=165,500
Select Real Estate
Decision Analysis
A-15
e. Maximin
Graphic Design (115,000+155,000+190,000+190,000)/4=170,000
Nursing (140,000+175,000+210,000+210,000)/4=187,500
Real Estate ( 95,000+135,000+230,000+230,000)/4=202,500<-Max
Medical Technology (120,000+180,000+210,000+210,000)/4=195,000
Culinary Technoloy ( 85,000+125,000+180,000+180,000)/4=170,000
Computer Information Technology (125,000+160,000+200,000+200,000)/4=186,250
Select Real Estate
Decision Analysis
Decision Making Under Risk

 Each possible state of nature has an

assumed probability
 States of nature are mutually exclusive
 Probabilities must sum to 1
 Determine the expected monetary value
(EMV) for each alternative
Decision Analysis
Expected Monetary Value
 a weighted average of decision outcomes in
which each future state of nature is assigned
a probability of occurrence

n
EV (x) =  p(xi)xi
i =1
where
xi = outcome i
p(xi) = probability of outcome i
Decision Analysis
Expected Monetary Value

EMV (Alternative i) = (Payoff of 1st state of nature)

x (Probability of 1st state of
nature)
+ (Payoff of 2nd state of nature)
x (Probability of 2nd state of
nature)
+ … + (Payoff of last state of
nature) x (Probability of
last state of nature)
Decision Analysis
Decision Making with Probabilities
Assume that it is now possible for the Southern Textile Company to estimate a
probability of 0.70 that good foreign competitive conditions will exist and a
probability of 0.30 that poor conditions will exist in the future. Determine the
best decision using expected value.

STATES OF NATURE
Good Foreign Poor Foreign
DECISION Competitive Conditions Competitive Conditions
Expand $ 800,000 $ 500,000
Maintain status quo 1,300,000 -150,000
Sell now 320,000 320,000

p(good) = 0.70 p(poor) = 0.30

EV(expand): $800,000(0.7) + 500,000(0.3) = $710,000
EV(status quo): 1,300,000(0.7) -150,000(0.3) = 865,000  Maximum
EV(sell): 320,000(0.7) + 320,000(0.3) = 320,000

Decision: Status quo

Decision Analysis
Decision Making Under Certainty

 Is the cost of perfect information worth it?

 Determine the expected value of perfect

information (EVPI)
Decision Analysis
Expected Value of Perfect Information (EVPI)
 EVPI is the difference between the payoff
under certainty and the payoff under risk

Expected value Maximum

EVPI = with perfect – EMV
information
Expected value with = (Best outcome or consequence for 1st state
perfect information of nature) x (Probability of 1st state of
(EVwPI) nature)
+ Best outcome for 2nd state of nature)
x (Probability of 2nd state of nature)
+ … + Best outcome for last state of nature)
x (Probability of last state of nature)
Decision Analysis
Expected Value of Perfect Information (EVPI)
 Good conditions will exist 70% of the time
choose maintain status quo with payoff of $1,300,000
 Poor conditions will exist 30% of the time
choose expand with payoff of $500,000
 Expected value given perfect information
= $1,300,000 (0.70) + 500,000 (0.30)
= $1,060,000
 Recall that expected value without perfect
information was $865,000 (maintain status
quo)
 EVPI= $1,060,000 - 865,000 = $195,000
Decision Analysis
Decision Trees

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 decision alternatives and
states of nature
5. Solve the problem by working backward
through the tree computing the EMV for
each state-of-nature node
Decision Analysis
Decision Trees
 A graphical method for analyzing decision
situations that require a sequence of
decisions over time
 Decision tree consists of
 Square nodes - indicating decision points
 Circles nodes - indicating states of nature
 Arcs - connecting nodes
Decision Analysis
Decision Tree Analysis
The Southern Textile Company is considering two alternatives: to expand its
existing production operation to manufacture a new line of lightweight material,
or to purchase land on which to construct a new facility in the future. Each of
these decisions has outcomes based on product market growth in the future
that will result in another set of decisions (during a 10-year planning horizon),
as shown in the following figure of a sequential decision tree. In this figure the
square nodes represent decisions, and the circle nodes reflect different states
of nature and their probabilities.

The first decision facing the company is whether to expand or buy land. If the
company expands, two states of nature are possible. Either the market will
grow (with a probability of 0.60) or it will not grow (with a probability of 0.40).
Either state of nature will result in a payoff. On the other hand, if the company
chooses to purchase land, three years in the future, another decision will have
to be made regarding the development of the land.

If the plant is expanded, two states of nature are possible - the market will
grow, with a probability of 0.60, or it will not grow, with a probability of 0.40. If
the market grows, the company will achieve a payoff of $2,000,000 over a 10-
year period. However, if no growth occurs, a payoff of only $225,000 will result.
Decision Analysis
Decision Tree Analysis
If the decision is to purchase land, two states of nature are possible. These
two states of nature and their probabilities are identical to that of plant
expansion; however, the payoffs are different. If market growth occurs for a
three-year period, no payoff will occur, but the company will make another
decision regarding development of the land. At that point, either the plant will
be expanded at a cost of $800,000 or the land will be sold, with a payoff of
$450,000. If no market growth occurs, there is no payoff, and another decision
situation becomes necessary - a warehouse can be constructed at a cost of
$600,000 or the land can be sold for $210,000.

If the plant is expanded after market growth, two states of nature are possible -
the market may grow, with a probability of 0.80, or it may not grow, with a
probability of 0.20. The payoffs for these two states of nature at the end of the
10-year period are $3,000,000 and $700,000, respectively.
If the company decides to build a warehouse, two states of nature can occur -
market growth can occur, with a probability of 0.30 and an eventual payoff of
$2,300,000, or no growth can occur, with a probability of 0.70 and a payoff of
$1,000,000.
Decision Analysis
Decision Tree Analysis
$2,000,000
0.60 Market growth
2
0.40
$225,000
$3,000,000

0.80
6
$700,000
0.20
1 4

$450,000
0.60 $2,300,000
3
0.40
0.30
7
0.70 $1,000,000
5

$210,000
Decision Analysis
Evaluations at Nodes
 Compute EV at nodes 6 & 7
EV(node 6)= 0.80($3,000,000) + 0.20($700,000) = $2,540,000
EV(node 7)= 0.30($2,300,000) + 0.70($1,000,000)= $1,390,000
 Decision at node 4 is between
$2,540,000 for Expand and
$450,000 for Sell land
 Choose Expand
 Repeat expected value calculations and decisions at
remaining nodes
Decision Analysis
Decision Tree Analysis
$1,290,000 $2,000,000
0.60 Market growth
2
0.40
$225,000
$3,000,000
$2,540,000
0.80
$1,740,000 6
$700,000
0.20
1 $1,160,000 4

$450,000
0.60 $2,300,000
$1,390,000
3
0.40
0.30
$790,000 7
$1,360,000
0.70 $1,000,000
5

$210,000
A-14 Decision Analysis
The Extron Oil Company is considering making a bid for a shale oil development
contract to be awarded by the federal government. The company has decided to
bid $110 million. The company estimates that it has a 60% chance of winning the
contract with this bid. If the firm wins the contract, it can choose one of three
methods for getting the oil from the shale: It can develop a new method for oil
extraction, use an existing (inefficient) process, or subcontract the processing out
to a number of smaller companies once the shale has been excavated. The results
from these alternatives are given as follows:
Develop New Process
Outcomes Probability Profit (millions)
Great Success 0.3 600
Moderate Success 0.6 300
Failure 0.1 -100
Use Present Process
Outcomes Probability Profit (millions)
Great Success 0.5 300
Moderate Success 0.3 200
Failure 0.2 -40
Subcontract
Outcomes Probability Profit (millions)
Moderate Success 1 250
The cost of preparing the contract proposal is $2,000,000. If the company does
not make a bid, it will invest in an alternative venture with a guaranteed profit of
$30 million. Construct a sequential decision tree for this decision situation and
determine whether the company should make a bid.
Decision Analysis

A-14

0.6
Decision Analysis

A-14

0.6