Lecture 05 - Decision Analysis with Uncertainty

# Lecture 05 - Decision Analysis with Uncertainty - Lecture 5...

This preview shows pages 1–12. Sign up to view the full content.

1 Lecture 5 Decision Analysis Uncertainty and Decision Making DADSS

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
2 Administrative Details Homework #3 Due Thursday Office hours  TA’s Monday and Wednesday 5:00-8:00 in  PH223 conference room Fischbeck’s Wednesday 1:30-3:00 in his  office PH208F Questions from last class? Readings are in the text, Chapter 10
3 Decision Problem Strong Moderate Weak Bonds 12 6 3 Stocks 15 3 -2 T-Bill 6.5 6.5 6.5 Choices States

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
4 Heuristics Optimist: Maxi-Max (best of the best) Pessimist: Maxi-Min (best of the worst) Mixture of optimism and pessimism Hurwicz with  α =percent optimist Rational (Laplace) all states equally likely:  Maxi-Average (best average) Regret: Mini-Max-Regret Satisficing
5 Failures of Simple Decision Rules Laplace, Hurwicz, Regret,  etc . are all  useful rules in many cases, but – like all  heuristics – they fail in certain cases The use of heuristic rules must include  recognition of their limitations

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
6 Min/Max Counterexample Optimism Pessimism Maximax Alt 1 9 8 9 Alt 2 10 -50,000 10 Maximin Alt 1 31 10,000 31 Alt 2 32 33 32
7 Regret Counterexample Payoffs Regret Minimax Alt 1 8 0 0 4 4 Alt 2 2 4 6 0 6 Payoffs Regret Minimax Alt 1 8 0 0 7 7 Alt 2 2 4 6 3 6 Alt 3 1 7 7 0 7 But suppose we now add another alternative…

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
8 Hurwicz Counterexample Alt 1 100 0 0 0 Alt 2 0 100 100 100 Which does the Hurwicz criterion indicate is the better project?
9 Laplace Counterexample Good Bad EV Alt 1 22 30 26 Alt 2 46 10 28 Suppose we’re uncertain about the weather: But what if we structured the problem as: Bad Weather Good Rain Fog Snow EV Alt 1 22 30 30 30 28 Alt 2 46 10 10 10 19

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
10 What’s Causing the Problems? These methods all give too little or too  non-specific attention to probabilities More importantly, their treatment of  probabilities can introduce biases and  distort answers We need a more general theory of  making decisions
11 Choice and Consequence

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 34

Lecture 05 - Decision Analysis with Uncertainty - Lecture 5...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online