Decision Theory

“CHOOSING THE RIGHT PATH”

MAKING STRATEGIC DECISIONS
&
“RUNNING THE PATH”
MANAGING RISKS AND OPPORTUNITIES
Faith
Hope
Guesswork
 Introduction to Decision Analysis
4

The field of decision analysis provides a

framework for making important decisions.
Decision analysis allows us to select a decision
from a set of possible decision alternatives
when uncertainties regarding the future exist.
The goal is to optimize the resulting payoff
in terms of a decision criterion.
 The Decision making Process

Identify & define Gather

The problem Information

Develop
alternatives

Evaluate
alternatives
Revise

Certainty Risk Uncertainty

Select
alternatives

Implement
decision

Evaluate
& control
 Structure of Decision making Problem

Decision Maker: individual or group selecting appropriate decision

Acts: Alternative courses of action or strategy

Events: outside the control of the decision maker

Payoff: net benefit or conditional economic consequences

Uncertainty: indefiniteness in outcome

Regret Table: Opportunity loss-diff. between highest possible profit

and the actual profit
Maximizing expected profit
 Introduction to Decision Analysis
9

Maximizing expected profit is a

common criterion when probabilities

can be assessed.

• Maximizing the decision maker’s utility function

is the mechanism used when risk is factored
into the decision making process.
 Payoff Table
10
Analysis

Payoff Tables

 Payoff table analysis can be applied when:

 There is a finite set of discrete decision alternatives.
 The outcome of a decision is a function of a single future event.
 In a Payoff table -
 The rows correspond to the possible decision alternatives.
 The columns correspond to the possible future events.
 Events (states of nature) are mutually exclusive and collectively
exhaustive.
 The table entries are the payoffs.
 The Scope of Decision Making
Decisional Inputs Metaorganization
(Objectives,
information, Organization
resources,
energy) Interactional
Group Levels

Individual

Permeable Decisional
Boundaries Outputs
(Actions
transactions,
outcomes)

External Environment
 Decision Making under Certainty

A manufacturer has 2 different machines M1 & M2

M1 M2
Set-up time (min.) 90 120
Tooling up cost Rs. 600 Rs. 1800
Machining time per piece 12 4
(min.)
Machine cost per hour 40 90
Question: Which of the two machines will you choose
to do the job if the order quantity is 1000 pieces.
 Answer

M1 M2
Set-up Time: (40/60)*90=60 Set-up Time: (90/60)*120=180
Tooling up Cost: 600 Tooling up Cost: 1800
Machine Time: (40/60)12000 Machine Time: (90/60)4000
Total=8660 Total=7980

Answer: Using M2 is the best decision

 Decision Making Under Risk
22

• The probability estimate for the occurrence of

each state of nature (if available) can be incorporated in
the search for the optimal decision.
• For each decision calculate its expected payoff.
 Decision Making Under Risk –
The Expected Value Criterion
23

For each decision calculate the expected payoff as

follows:

Expected Payoff = S(Probability)(Payoff)

(The summation is calculated across all the states of nature)

Select the decision with the best expected payoff

When to use the expected value approach
24

The expected value criterion is useful generally

in two cases:
 Long run planning is appropriate, and decision
situations repeat themselves.
 The decision maker is risk neutral.
 Decisions with Risk

Probability can be assigned based on

a. Logic or deduction: This is Objective probability.
This reflects the historical evidence. Ex. Getting
head/tail for a tossed coin. Or getting a number on
rolling dice etc.
b. Past experience is with empirical evidence.
c. Subjective estimate due to intelligence or intuition.
When the decision maker has access to probability
information, the criterion for decision making is to
maximize s the expected value of the decision.
 Decision making under Risk

A Departmental store purchases Christmas trees which

can be ordered only in lots of 100. Each tree costs 25 Rs
and sells at 40 Rs. each. Unsold trees have no salvage
value. The probability distribution obtained from analysis
of past sales data is given below:
Trees sold Probability
100 .2
200 .35
300 .25
400 .15
500 .05
How much Quantity should the Departmental stores buy
to maximize profit
 Steps to Solve

Step 1: Identify Strategies (S)- Buy qnt.

Step 2: List Events (N)- Demand qnt.
Step 3:Estimate probability corresponding to each
event
Step 4: Determine Payoff table
Step 5: Find Expected Monetary Value (EMV)

Trees sold Probability

100 .2
200 .35
300 .25
400 .15
500 .05
x=quantity of trees bought
y=demand for the trees
c=cost per unit
s=selling price per unit

1. y ≥x: Payoff= (s-c)x [e.g. bought 100; demand 200]

2. y<x: Payoff= (s-c)y-(x-y)c [e.g. bought 300; demand 100]
 Available Events
Strategies
N1 N2 N3 N4 N5
0.2 0.35 0.25 0.15 0.05
S1 100 1500 1500 1500 1500 1500

S2 200 -1000 3000 3000 3000 3000

S3 300 -3500 500 4500 4500 4500

S4 400 -6000 -2000 2000 6000 6000

S5 500 -8500 -4500 -500 3500 7500

x=quantity of trees bought

y=demand for the trees
c=cost per unit
s=selling price per unit

1. y ≥x: Payoff= (s-c)x [e.g. bought 100; demand 200]

2. y<x: Payoff= (s-c)y-(x-y)c [e.g. bought 300; demand 100]
 Expected Monetary Values

 EMV (S1)= (S1N1×p1) + (S1N2×p2) +…….+ (S1N5×p5)= 1500

 EMV (s2)= 2200
 EMV(s3)=1500
 EMV(s4)=-200
 EMV(s5)=-2500
 S2 gives maximum profit which is 200 trees
 Decision Making Under Uncertainty
31

The decision criteria are based on the decision maker’s

attitude toward life.
The criteria include the
 Maximin Criterion - pessimistic or conservative approach.
 Minimax Regret Criterion - pessimistic or conservative
approach.
 Maximax Criterion - optimistic or aggressive approach.

 Principle of Insufficient Reasoning – no information about

the likelihood of the various states of nature.
 Decisions under Uncertainty

Uncertainty : The decision maker has absolutely no

knowledge of the probability of outcome of each
alternative.
When no information exists the personality characteristics
of the decision maker become more important for
determining which decision is made. The following five
characteristics describe what most of the dm’s do.
a. Optimistic Decisions
b. Pessimistic Decisions
c. Realistic decisions.
d. Regret minimizing Decisions.
e. Insufficient Reasoner
 Criteria of Decision making

a. Optimistic Decisions The DM think optimistically about the

event that influence decisions. They choose the alternative that
maximizes the outcome
b. Pessimistic Decisions They believe that worst possible
outcome will occur no matter what they do. They estimate the
worst outcomes associated with each alternative and select the
best of these worst outcomes.
c. Realistic Decisions. They take the middle path neither
optimistic nor pessimistic.
d. Regret minimizing Decisions. They want to minimize the
dissonance they experience
e. Insufficient Reason Decisions. These are also called eqi-
probable decision maker. They assume that all the possible
outcomes have equal chance of occurring.
 Decision Criteria under Uncertainty
An Inventory Problem:
A Newspaper Seller thinks of selling a new Entertainment Magazine to his regular
customers. He believes that he can sell 9-12 copies.
Cost Price = 8 Selling Price = 12
Magazines that are not sold can be returned for a refund of 50%.

 MAXIMIN CRITERIA - pessimistic or conservative

approach.
 MAXIMAX CRITERIA- optimistic or aggressive
approach.
 MINIMAX REGRET CRITERIA - pessimistic or
conservative approach.
 LAPLACE CRITERIA
 HURWICZ ALPHA CRITERIA
Decision Making Under Uncertainty - The Maximin Criterion
35

This criterion is based on the worst-case scenario.

 It fits both a pessimistic and a conservative decision
maker’s styles.
 A pessimistic decision maker believes that the worst possible
result will always occur.
 A conservative decision maker wishes to ensure a guaranteed
minimum possible payoff.
 The Maximin Criterion
DECISION MATRIX

Maximin
STATES OF NATURE
STRATEGIES Criteria
(PURCHASE)
N1=9 N2= 10 N3= 11 N4= 12 Minimum
Payoff
S1=9 36 36 36 36 36
S2=10 32 40 40 40 32
S3=11 28 36 44 44 28
S4= 12 24 32 40 48 24
S= QUANTITY STOCKED P=PROFIT
N=DEMAND L=LOSS
 PESSIMISTIC
 CONSERVATIVE DECISION MAKER’S STYLE
 WORST CASE SCENARIO
 A GUARANTEED MINIMUM POSSIBLE PAYOFF
Decision Making Under Uncertainty - The Maximax Criterion
37

This criterion is based on the best possible scenario.

It fits both an optimistic and an aggressive decision
maker.

An optimistic decision maker believes that the best

possible outcome will always take place regardless of
the decision made.

An aggressive decision maker looks for the decision

with the highest payoff (when payoff is profit).
 Decision Making Under Uncertainty -
The Maximax Criterion
38

To find an optimal decision.

 Find the maximum payoff for each decision alternative.
 Select the decision alternative that has the maximum of the
“maximum” payoff.
 The Maximax Criterion
Maximax
STATES OF NATURE Criteria
STRATEGIES
(PURCHASE) N1=9 N2= 10 N3= 11 N4= 12
Maximum
Payoff
S1=9 36 36 36 36 36
S2=10 32 40 40 40 40
S3=11 28 36 44 44 44
S4= 12 24 32 40 48 48

 BEST POSSIBLE SCENARIO

 OPTIMISTIC & AGGRESSIVE DECISION MAKER
 BEST POSSIBLE OUTCOME REGARDLESS OF THE DECISION
 HIGHEST PAYOFF
Decision Making Under Uncertainty - The Minimax Regret Criterion
40

 The Minimax Regret Criterion

 This criterion fits both a pessimistic and a
conservative decision maker approach.
 The payoff table is based on “lost
opportunity,” or “regret.”
 The decision maker incurs regret by failing
to choose the “best” decision.
Decision Making Under Uncertainty - The Minimax Regret Criterion
41

The Minimax Regret Criterion

 To find an optimal decision, for each state of nature:
 Determine the best payoff over all decisions.
 Calculate the regret for each decision alternative as the
difference between its payoff value and this best payoff value.
 For each decision find the maximum regret over all states
of nature.
 Select the decision alternative that has the minimum of
these “maximum regrets.”
 The Minimax Regret Criterion

STATES OF NATURE
STRATEGIES
(PURCHASE) N1=9 N2= 10 N3= 11 N4= 12

S1=9 36 36 36 36
S2=10 32 40 40 40
S3=11 28 36 44 44
S4= 12 24 32 40 48
REGRET MATRIX MAXIMUM
STRATEGY EVENTS REGRET MINIMAX
  N1=9 N2= 10 N3= 11 N4= 12    
S1=9 0 4 8 12 12  
S2=10 4 0 4 8 8 8
S3=11 8 4 0 4 8 8
S4= 12 12 8 4 0 12  

 BOTH PESSIMISTIC AND CONSERVATIVE

 LOST OPPORTUNITY-REGRET
 Three types of Decision Makers
43

Risk Averse -Prefers a certain outcome to a

chance outcome having the same expected value.

Risk Taking - Prefers a chance outcome to a

certain outcome having the same expected value.

Risk Neutral - Is indifferent between a chance

outcome and a certain outcome having the same
expected value.
 LAPLACE & HURWITZ ALPHA CRITERIA

STATES OF NATURE EMV EMV

STRATEGIES
(PURCHASE) α
N1=9 N2= 10 N3= 11 N4= 12 P
0.4
0.25
S1=9 36 36 36 36
36 36
S2=10 32 40 40 40
38 35.2
S3=11 28 36 44 44
38 34.8
S4= 12 24 32 40 48
36 33.6

 NEITHER PESSIMISTIC NOR OPTIMISTIC

 LAPLACE - All states of nature are equally likely to occur.
 HURWITZ ALPHA - set α between 0 and 1 according to level of optimism
THANK YOU