University of Minnesota, Twin Cities School of Statistics
Title: Computing the Joint Range of a Set of Expectations
Authors: Charles J. Geyer, Radu C. Lazar, and Glen D. Meeden
Affiliation: School of Statistics, University of Minnesota
Abstract: In the theory of imprecise probability it is often of interest to find the range of the expectation of some function over a convex family of probability measures. Here we show how to find the joint range of the expectations of a finite set of functions when the underlying space is finite and the family of probability distributions is defined by finitely many linear constraints.
Key words and phrases: linear constraints, probability assessment, convex family of priors, polytope
Complete text of the current version of the paper as PostScript or as PDF.
Software: The software package used by the paper is rcdd.
Rweb: A web page with one of the examples in the paper allows users to try the example on-line and also modify the example to see how our methods work.