Engineering Management

Topic 2

Decision-Making and Analysis

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-1
 Outline
 The Decision Process in Operations
 Fundamentals of Decision Making
 Decision Tables
 Decision Making under Uncertainty
 Decision Making Under Risk
 Decision Making under Certainty
 Expected Value of Perfect Information ( EVPI)
 Decision Trees
 A More Complex Decision Tree

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-2
Models, and the Techniques of Scientific
Management
 Can Help Managers To:
 Gain deeper insight into the nature of business
relationships
 Find better ways to assess values in such
relationships; and
 See a way of reducing, or at least understanding,
uncertainty that surrounds business plans and
actions

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-3
 Steps to Good Decisions
 Define problem and influencing factors
 Establish decision criteria
 Select decision-making tool (model)
 Identify and evaluate alternatives using decision-
making tool (model)
 Select best alternative
 Implement decision
 Evaluate the outcome

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-4
 Models
 Are less expensive and disruptive than
experimenting with the real world system
 Allow operations managers to ask “What if” types of
questions
 Are built for management problems and encourage
management input
 Force a consistent and systematic approach to the
analysis of problems
 Require managers to be specific about constraints
and goals relating to a problem
 Help reduce the time needed in decision making
Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-5
 Limitations of Models
They
 may be expensive and time-consuming to develop
and test
 are often misused and misunderstood (and feared)
because of their mathematical and logical complexity
 tend to downplay the role and value of
nonquantifiable information
 often have assumptions that oversimplify the
variables of the real world

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-6
 The Decision-Making Process
Quantitative Analysis
Logic
Historical Data
Marketing Research
Problem Scientific Analysis Decision
Modeling

Qualitative Analysis
Emotions
Intuition
Personal Experience
and Motivation
Rumors

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-7
 Ways of Displaying
a Decision Problem
 Decision trees
Outcomes
 Decision tables
States of Nature
The three types of
decision models:
Alternatives

 Under uncertainty Decision Problem

 Under risk
 Under certainty

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-8
 Fundamentals of
Decision Theory - continued
Terms:
 Alternative: course of action or choice
 State of nature: an occurrence over which the decision
maker has no control

Symbols used in decision tree:

 A decision node from which one of several alternatives may
be selected
 A state of nature node out of which one state of nature will
occur
Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-9
 Getz Products Decision Tree

A state of nature node Favorable market

1
r u ct t Unfavorable market
n st lan
A decision node Co ge p Favorable market
lar
Construct
small plant 2
Do Unfavorable market
no
t hi
ng

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-10
 Decision Table

States of Nature
Alternatives State 1 State 2

Alternative 1 Outcome 1 Outcome 2

Alternative 2 Outcome 3 Outcome 4

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-11
 Decision Making Under Uncertainty

 Maximax - Choose the alternative that maximizes

the maximum outcome for every alternative
(Optimistic criterion)
 Maximin - Choose the alternative that maximizes
the minimum outcome for every alternative
(Pessimistic criterion)
 Equally likely - chose the alternative with the
highest average outcome.

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-12
 Example - Decision Making Under
Uncertainty
States of Nature
Alternatives Favorable Unfavorable Maximum Minimum Row
Market Market in Row in Row Average
Construct $200,000 -$180,000 $200,000 -$180,000 $10,000
large plant
Construct $100,000 -$20,000 $100,000 -$20,000 $40,000
small plant
Do nothing $0 $0 $0 $0 $0
Maximax Maximin Equally
likely

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-13
 The Decisions
1. The maximax choice is to construct a large plant.
This is the maximum of the maximum number within
each row or alternative.
2. The maximin choice is to do nothing. This is the
maximum of the minimum number within each row or
alternative.
3. The equally likely choice is to construct a small plant.
This is the maximum of the average outcomes of
each alternative. This approach assumes that all
outcomes for any alternative are equally likely.

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-14
 Decision Making Under Risk

 Probabilistic decision situation

 States of nature have probabilities of occurrence
 Select alternative with largest expected monetary
value (EMV)
 EMV = Average return for alternative if decision were
repeated many times

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-15
 Expected Monetary Value Equation
Number of states of nature

Value of Payoff
N
EMV ( A j ) =  X i * P (X i ) Probability of payoff
i =1

= X 1 * P (X 1 ) + X 2 * P (X 2 ) + ... +X N * P (X N )

Alternative i
Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-16
 Example - Decision Making Under
Uncertainty
States of Nature
Alternatives Favorable Unfavorable Expected
Market Market P(0.5) value
P(0.5)
Construct $200,000 -$180,000 $10,000
large plant
Construct $100,000 -$20,000 $40,000 Best choice
small plant
Do nothing $0 $0 $0

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-17
 Expected Value of Perfect
Information (EVPI)
 EVPI places an upper bound on what one would
pay for additional information
 EVPI is the expected value with certainty minus
the maximum EMV

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-18
 Expected Value With Perfect
Information (EV|PI)
Expected value under certainty
in
  Best outcome for the ith state of nature *P( S i )
i 1

where P(S i )  Probability of the ith state of nature

and i  1 to n, the number of states of nature

EVPI = Expected value under Certainty - maximum EMV

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-19
 Expected Value of Perfect
Information
State of Nature
Alternative Favorable Unfavorable
EMV
Market ($) Market ($)
Construct a 200,000 -$180,000 $20,000
large plant
Construct a small
plant $100,000 -$20,000 $40,000

Do nothing $0 $0 $0

Probabilities 0.50 0.50

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-20
 Expected Value of Perfect
Information
EVPI = expected value with perfect information -
max(EMV)

= $200,000*0.50 + 0*0.50 - $40,000

= $60,000

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-21
 Decision Trees
 Graphical display of decision process
 Used for solving problems
 With one set of alternatives and states of nature,
decision tables can be used also
 With several sets of alternatives and states of nature
(sequential decisions), decision tables cannot be used
 EMV is criterion most often used

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-22
 Analyzing Problems with Decision
Trees
 Define the problem
 Structure or draw the decision tree
 Assign probabilities to the states of nature
 Estimate payoffs for each possible combination of
alternatives and states of nature
 Solve the problem by computing expected
monetary values for each state-of-nature node

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-23
 Decision Tree

State 1
Outcome 1
v e 1 1 State 2
na ti Outcome 2
lt er
A
Alte
rna
tive State 1
2 Outcome 3
2 State 2
Outcome 4
Decision
Node
State of Nature Node
Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-24
 Getz Products Decision Tree
Completed and Solved
Payoffs
EMV for node 1 = $10,000
Favorable market (0.5)
$200,000
1
r u ct t Unfavorable market (0.5)
ts an
n pl -$180,000
o
C ge
lar
Favorable market (0.5) $100,000
Construct
small plant 2
Do Unfavorable market (0.5)
no -20,000
t hi EMV for node 2 = $40,000
ng

0
Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-25
 Getz Products Decision Tree with
Probabilities and EMVs Shown
1st decision 2nd decision point $106,000 Fav. Mkt (0.78)
$190,000
point plant 2

$106,400
Unfav. Mkt (0.22)
La r g e -$190,000
Small $63,600 Fav. Mkt (0.78)
$90,000
r. R
.
es )
5 No lant
p 3 Unfav. Mkt (0.22)
$30,000
Su s. (.4 pla
nt
Po $10,000
-$87,400 Fav. Mkt (0.27)
1 $190,000
an t 4
Sur Unfav. Mkt (0.73)
Neg . Res. e p l -$190,000
y

. (.5 Larg
Surve

$2,400
5) Small $2,400 Fav. Mkt (0.27)
$90,000
No plant 5 Unfav. Mkt (0.73)
$49,200

pla $30,000
nt $10,000
$10,000 Fav. Mkt (0.5)
No $200,000
s
lant 6
ur v Unfav. Mkt (0.5)
ey p -$180,000
e
$40,000

Larg $40,000 Fav. Mkt (0.5)

Small $100,000
No p plant
7 Unfav. Mkt (0.5)
$20,000
lant
$0
Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-26
 Discussion on Topic 3

 Who makes the decision? Decision Nodes

 Examples of decisions made by companies
 Application of decision making model
 Reaching certainty
 Produce a model for decision making and work
out the solution…

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-27
 Example
A soft drink vendor created the following table of conditional values

Demand
High Moderate low
Large stock $ 22 000 $ 12 000 $ (2 000)
Average stock $ 14 000 $ 10 000 $ 6 000

Small stock $ 9 000 $ 8 000 $ 4 000

The probabilities associated to high, moderate and low demand is 0.3, 0.5, and
0.2 respectively
 Work out best decision based on EMV
 The EVPI

A-28
 Examples
Example A5/A6
A13
A20

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-29
 Example 2
 ABC is considering building a sensitive new airport scanning device.
Managers believe that there is a probability of 0.4 that ATR will come
out with a competitive product. If ABC adds an assembly line for the
product and ATR does not follow with a competitive product, ABC
expected profit is $40,000; if ABC adds an assembly line and ATR
follows suit, ABC still expects $10,000 profit. If ABC add a new plant
and ATR does not produce a competitive product, ABC expects a
profit of $600,000; if ATR does compete for the market, ABC expects
a loss of $100,000.
 Work out the EMV for each decision
 Work out the EVPI

Transparency Masters to accompany Heizer/Render – Principles of © 2004 by Prentice Hall, Inc., Upper Saddle River, N.J. 07458
Operations Management, 5e, and Operations Management, 7e A-30
Dick Holiday is not sure what he should do. He can build either a large
video rental section or a small one in his drugstore. He can also gather
additional information or simply do nothing. If he gathers additional info
the results could suggest either a favourable or an unfavourable
market, but it would cost him $3,000 to gather the info. He believes that
there is a 50:50 chance that the info will be favourable. If the rental
market is favourable, Holiday will earn $15,000 with a large section or
$5,000 with a small. With an unfavourable video market, however
Holiday could lose $20,000 with a large section and $10000 with a
small section. Without gathering additional info, Holiday estimates that
the probability of a favorable rental is 0.7. A favourable report from the
study will increase the probability of a favourable rental market to 0.9.
Furthermore an unfavourable report from the additional info would
decrease the prob of a favourble market to 0.4. Of course Holiday
could forget all these numbers and do nothing. What is your advice to
Holiday. A-31