{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# week10da - Spring 2010 DecisionAnalysis MS405 Conflicting...

This preview shows pages 1–6. Sign up to view the full content.

Kemal Kılıç, Sabancı Üniversitesi Kemal Kılıç, Sabancı Üniversitesi Spring Spring , 2010 , 2010 Decision Analysis   MS 405    Conflicting Objectives I Kemal Kılıç Faculty of Engineering and Natural Sciences Week 10 1

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

View Full Document
Kemal Kılıç, Sabancı Üniversitesi Kemal Kılıç, Sabancı Üniversitesi Spring Spring , 2010 , 2010 The risk and return trade-offs? How to model a decision maker’s preferences? Using Utilities to Model Risk Attitudes Risk Averse, Risk Lover, Risk Neutral Expected Utility, Certainty Equivalents and Risk Premiums Utility Function Assessment Using Certainty Equivalents Using Probabilities Risk Tolerance and the Exponential Utility Function Utility theory axioms and paradoxes Week 10 2 Review – Ch. 13&14 (Risk Attitudes & Utility)
Kemal Kılıç, Sabancı Üniversitesi Kemal Kılıç, Sabancı Üniversitesi Spring Spring , 2010 , 2010 Methods to deal with multiple conflicting objectives. Decide how best to trade off increased value on one objective for lower value on another. Additive preference model Weighted sum of the utility of each objective Elements of the additive utility function How to compare attribute levels? – Finding utilities, a common score for each attribute i) Proportional Scoring ii) Ratios iii) Std. Utility Function Assessment How important each objective (attribute)? – Finding weights i) Pricing out ii) Swing Weighting iii) Lottery Weights This Week – Ch. 15(Conflicting Objectives) Week 10 3

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

View Full Document
Kemal Kılıç, Sabancı Üniversitesi Kemal Kılıç, Sabancı Üniversitesi Spring Spring , 2010 , 2010 Nominal Scale In a nominal scale, names (which may be numbers) are given to things just to label and classify them. Dividing people into male and female is a nominal scale. Putting numbers on buses to identify the route is a nominal scale. Putting numbers on football players to identify their position on the field is a nominal scale. Arithmetical operations are meaningless on nominal scales. To add a 44 bus to a 102 bus and get a 146 bus is nonsense. There is no order as well. Bus 102 is greater then Bus 44 is also nonsense. No preference information . Week 10 4
Kemal Kılıç, Sabancı Üniversitesi Spring Spring , 2010 , 2010 Ordinal Scale The ordinal scale puts things in an order or rank, as well as labelling and classifying them. House numbers are usually on an ordinal scale because 1 is usually at the beginning of the road and the higher the number the further down the road it is. There is preference information but arithmetic means make no sense. Constructed scales in Decision Analysis are often “ordinal”. Week 10

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 / 57

week10da - Spring 2010 DecisionAnalysis MS405 Conflicting...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online