Transcript Decision Analysis - University of San Francisco
Decision Analysis
How to make a difficult decision?
Uncertainty regarding the future Conflicting values or objectives Goal of Decision Analysis: – Help people make good decisions
Good Decisions vs Good Outcomes
Good decisions don’t always result in good outcomes Not necessarily the fault of the decision maker A structured approach to decision making should lead to more good outcomes than if decisions were made haphazardly
Characteristics
Decisions Alternatives States of nature
Decisions
Decision must involve at least 2 alternatives – Alternative: course of action intended to solve a problem
Alternatives
Alternatives are evaluated on the basis of the value added to one or more decision criteria – Criteria: various factors that are important to the decision maker and influenced by the alternatives
States of Nature
States of nature correspond to future events that are not under the decision maker’s control
Magnolia Inns Example
Decision Alternatives – Buy at A – Buy at B – Buy at A & B – Buy nothing States of Nature – Airport built at A – Airport built at B
Magnolia Inns Cash Flow
Current purchase price Present value of future cash flows if hotel and airport are built at this location Parcel of Land Near Location A $18 B $12 $31 $23 Present value of future sales price of parcel if the airport is not built at this location $6 $4 (Note: All values are in millions of dollars.)
Payoff Matrix
Land Purchased Airport is Built at Location at Location(s) A B A B A&B None $13 ($8) $5 $0 ($12) $11 ($1) $0
Maximax Decision Rule
Alternative with largest payoff
Land Purchased Airport is Built at Location at Location(s) A B A B A&B None $13 ($8) $5 $0 ($12) $11 ($1) $0
Maximin
Alternative with largest minimum payoff – Hedge against worst possible outcome
Land Purchased Airport is Built at Location at Location(s) A B A B A&B None $13 ($8) $5 $0 ($12) $11 ($1) $0
Expected Monetary Value (EMV)
Decision alternative with largest EMV
Land Purchased Airport is Built at Location at Location(s) A B A B A&B None $13 ($8) $5 $0 ($12) $11 ($1) $0 EMV ($2) $3.4
$1.4
$0
Example:
40% chance A, 60% chance B
Sensitivity Analysis
Prob. Of location A
0 0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
EMV A
-$2.0
-$12.0
-$9.5
-$7.0
-$4.5
-$2.0
$0.5
$3.0
$5.5
$8.0
$10.5
$13.0
EMV B
$3.4
$11.0
$9.1
$7.2
$5.3
$3.4
$1.5
-$0.4
-$2.3
-$4.2
-$6.1
-$8.0
EMV A&B EMV None
$1.4
$0.0
-$1.0
-$0.4
$0.0
$0.0
$0.2
$0.8
$1.4
$2.0
$2.6
$3.2
$3.8
$4.4
$5.0
$0.0
$0.0
$0.0
$0.0
$0.0
$0.0
$0.0
$0.0
$0.0
Expected Value of Perfect Info
EV of PI = EV with PI – max EMV
Decision Trees
Decision nodes Event nodes Terminal nodes Magnolia Inns Example (page 731)
TreePlan
Excel add-in from Prof. Mike Middleton