Skip to main content
Conference paper - Peer-reviewed, 2007

Distributions over Expected Utilities in Decision Analysis

Ekenberg, Love; Andersson, Mikael; Danielson, Mats; Larsson, Aron

Abstract

It is often recognised that in real-life decision situations, classical utility theory puts too strong requirements on the decision-maker. Various interval approaches for decision making have therefore been developed and these have been reasonably successful. However, a problem that sometimes appears in real-life situations is that the result of an evaluation still has an uncertainty about which alternative is to prefer. This is due to expected utility overlaps rendering discrimination more difficult. In this article we discuss how adding second-order information may increase a decision-maker’s understanding of a decision situation when handling aggregations of imprecise representations, as is the case in decision trees or influence diagrams

Keywords

Decision analysis; Imprecise probabilities; Imprecise utilities; Hierarchical models

Published in

Conference

5th International Symposium on Imprecise Probability: Theories and Applications

Authors' information

Andersson, Mikael (Andersson, Mikael)
Swedish University of Agricultural Sciences, Department of Economics
Danielson, Mats
Ekenberg, Love
Larsson, Aron

URI (permanent link to this page)

https://res.slu.se/id/publ/31179