Scribd
Upload
16 views2 pages

DECISION THEORY Intro

The document discusses decision theory and outlines four criteria or models for making decisions under conditions of uncertainty: 1. The Maximax Criterion (Optimistic Criterion) which selects the alternative with the maximum of the maximum payoffs. 2. The Maximin Criterion (Pessimistic Criterion) which selects the alternative with the maximum of the minimum payoffs. 3. The Minimax Regret Criterion which calculates regret for each payoff and selects the alternative with the minimum of the maximum regrets. 4. The Criterion of Realism which is a weighted average of the maximum and minimum payoffs for each alternative and selects the alternative with the maximum

Uploaded by

allana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
16 views2 pages

DECISION THEORY Intro

The document discusses decision theory and outlines four criteria or models for making decisions under conditions of uncertainty: 1. The Maximax Criterion (Optimistic Criterion) which selects the alternative with the maximum of the maximum payoffs. 2. The Maximin Criterion (Pessimistic Criterion) which selects the alternative with the maximum of the minimum payoffs. 3. The Minimax Regret Criterion which calculates regret for each payoff and selects the alternative with the minimum of the maximum regrets. 4. The Criterion of Realism which is a weighted average of the maximum and minimum payoffs for each alternative and selects the alternative with the maximum

Uploaded by

allana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

DECISION THEORY(Sourced from Levin,et.al.

,Quantitative Approaches to Management book)

Decision Making
- a process of arriving at a course of action
Steps : 1.) List all viable Alternatives (to be done).
2.) List the future events (affecting demand) that may occur(States of nature).
3.) Construct a pay-off table ( a table which shows the pay-offs expressed as profits or any other
measure of benefit appropriate to the situation).
Example . A manufacturer considering methods of expanding its production in order to
accommodate an increasing demand.
Alternatives States of Nature
Expand( the existing Plant) High demand(high product acceptance)
Build (another Plant) Moderate demand- reasonable product acceptance but
(enter into a)Subcontract Low demand- low product acceptance
Do Nothing (may not be included) Failure- no acceptance
Environments in which decisions are made
1. Under conditions of Certainty – only one state of nature exists; there is complete certainty about the
future.
2. Under conditions of Uncertainty – more than one state of nature exist but the decision maker has no
information about the various states of nature, not even enough knowledge to assign probabilities
3. Under conditions of Risk – more than one state of nature exist but the decision maker has information
that will permit the assignment of probabilities to the states of nature.

Criteria(or models) under conditions of Uncertainty


1. The Maximax Criterion (Optimistic Criterion)
“best among the best criterion” ; maximum among the maximum value for each alternative
Refer to the pay-off chart below for example .
Decision maker’s Alternatives
States of Nature Expand Build Subcontract
High P5 M P7 M P3M
Moderate P2.5M P3M P1.5M
Low -P2.5M -P4M -P100,000
Failure -P4.5M -P8M -P1M
Highest pay-off for each alternative
Expand: P5M
Build : P7M  maximum among these highest pay-offs
Subcontract: P3M
Decision : Build
2. The Maximin Criterion (Pessimistic Criterion)
“best among the worst criterion” ; maximum among the minimum value for each alternative
Refer to the pay-off chart below for example .
Decision maker’s Alternatives
States of Nature Expand Build Subcontract
High P5 M P7 M P3M
Moderate P2.5M P3M P1.5M
Low -P2.5M -P4M -P100,000
Failure -P4.5M -P8M -P1M
Lowest pay-off for each alternative
Expand: -P4.5M
Build : -P8M
Subcontract: -P1M  maximum among these lowest pay-offs
Decision : Subcontract
3. The Minimax Regret Criterion
Refer to the pay-off chart below for example .
Decision maker’s Alternatives
States of Nature Expand Build Subcontract
High P5 M P7 M P3M P7M is the highest
Moderate P2.5M P3M P1.5M P3M is the highest
Low -P2.5M -P4M -P100,000 -P100000 is the highest
Failure -P4.5M -P8M -P1M -P1M is the highest
For each state of Nature, subtract the highest pay-off by every pay-off in that state(The result is the
regret).Then for each alternative, choose the maximum regret and select the minimum of these
maximum regrets.
Construct a Regret Table
Decision maker’s Alternatives
States of Nature Expand Build Subcontract
High P7M-P5M=P2M P7 M-P7M= 0 P7M-P3M= P4M
Moderate P3M-P2.5M = P0.5M P3M-P3M= 0 P3M-P1.5M= P1.5M
Low -P100000-(-P2.5M)= P2.4M -P100000-(-P4M)= P3.9M -P100000-(-P100000) = 0
Failure -P1M-(-P4.5M) =P3.5M -P1M-(-P8M)= P7M -P1M-(-P1M)= 0
Choose the maximum regret for each alternative
Expand: P3.5M  minimum among these maximum regrets
Build : P7M
Subcontract: P4M
Decision : Expand
4. The Criterion of Realism
For each alternative, use the formula
Measure of Realism = maximum pay-off X  + minimum pay-off X (1- )
Refer to the pay-off chart below for example .
Decision maker’s Alternatives
States of Nature Expand Build Subcontract
High P5 M P7 M P3M
Moderate P2.5M P3M P1.5M
Low -P2.5M -P4M -P100,000
Failure -P4.5M -P8M -P1M

If Given  = 0.70 , then 1- =0.30


Expand: P5M X 0.70 + -P4.5M X 0.30= P2.15M
Build : P7M X 0.70 + -P8M X 0.30 = P2.5M  maximum value
Subcontract: P3M x 0.70 + -P1M X 0.30 = P1.8M
Decision : Build

You might also like