Professional Documents
Culture Documents
Analysis
This chapter will covers:
• Problem Definition
• Problem Scope
• Resources, time & cognitive limitation
• Problem Structure
• Choices, Uncertainties, Objectives
• Structuring Tools
• Decision analysis of a few alternatives using
Influence diagrams, AHP or decision trees
Problem definition and structuring
Structuring a decision problem by
representing the inter-relationships Define
problems
Uncertain
decision objectives
events
Structuring Decision Problem
• Decision problems include three types of elements: decisions,
uncertain events and objectives.
• Decisions (Objectives)
• A choice between two or more alternatives.
• Uncertain events
• A situation outside the control of the decision maker that
could result in two or more possible outcomes
• Alternatives (Choices)
• A criterion for evaluating the desirability of a situation.
INFLUENCE DIAGRAMS
Uncertain
Event
Decisions
• is a choice between two or more alternatives
Alternative A
Outcome A
Alternative B Outcome B
Decision
Outcome C
Alternative C
Influence Diagrams
Uncertain Events
is a situation outside the control of the decision maker that
could result either two or more possible outcomes.
Price A
sales
Uncertain
Price B
event
Price C
Influence Diagrams: Example
Unit Price
~ Income
Amount used in
Advertisement Units Sold
Profit
Chance
node Event 1
Decision
ion 1 Event 2
node Decis
Event 3
Dec
is ion 2
Buying second-hand Car
Structuring Tools
Decision Tree
Another diagram that models choices and uncertainties and can
be extended to include multiple and sequential decisions.
Price C
Decision Analysis: A Few Alternatives
• Decision trees
• Graphical representation of
relationships
• Multiple criteria approach
• Demonstrates complex
relationships
• Cumbersome, if many
alternatives exists
Decision Analysis: A Few Alternatives
Investment example
Tabular representation:
Canned Food from the pineapple harvest are currently being
processed at XYZ Sdn Bhd. The manager has found a case of
cans that have not been properly sealed. There are three lines
that processed cans of this type and the manager wants to
know which line is most likely to be responsible for this
mistake.
Assume the manager has the information as follow:
P(Line2/Defective)=(0.4*0.05)/0.0725 = 0.4828
Example 1: Jenny Lind
#1
Payouts and Probabilities
#2
Jenny Lind - Payoff Table
States of Nature
Small Box Medium Large Box
Decisions Office Box Office Office
Sign with
Movie $200,000 $1,000,000 $3,000,000
Company
Sign with TV
$900,000 $900,000 $900,000
Network
Prior
0.3 0.6 0.1
Probabilities
#3
Jenny Lind - How to Decide?
• Maximax ?
• Maximin?
• Expected Return?
#5
Using Expected Return Criteria
EVmovie=0.3(200,000)+0.6(1,000,000)+0.1(3,000,000)
= $960,000 ( EVBest)
EVtv =0.3(900,000)+0.6(900,000)+0.1(900,000)
= $900,000
Therefore, using this criteria, Jenny should select the
movie contract.
Assumption
#3
Expected Value of Perfect
Information (EVPI)
#1
EVPI Calculation
#1
Modeling the problem
• Alternatives:
• Purchasing the airplane
• Renting the airplane
• Investing in a bank
• Objectives?
• Company Growth, Greater influence in the community,
Maximizing Profit
• If the probability of various unknown such as
operating cost, amount of business ,etc is known then
an decision tree or influence diagram can be used to
structure the problem.
#2
Initial influence diagram
Inputs
Inputs
Inputs
Intermediate
Consequence node
calculations
#3
Variables
#4
One Way Sensitivity Analysis
#4
One way Sensitivity graph for hours flown
The fact that the company believes that the hours flown could be
above or below 664 suggests that this is a crucial variable.
#5
Conclusion…..