Connecting Dempster–Shafer Belief Functions with Likelihood-based Inference
Author: Aickin, M.
Source: Synthese, Volume 123, Number 3, June 2000 , pp. 347-364(18)
Abstract:The Dempster–Shafer approach to expressing belief about a parameter in a statistical model is not consistent with the likelihood principle. This inconsistency has been recognized for some time, and manifests itself as a non-commutativity, in which the order of operations (combining belief, combining likelihood) makes a difference. It is proposed here that requiring the expression of belief to be committed to the model (and to certain of its submodels) makes likelihood inference very nearly a special case of the Dempster–Shafer theory.
Document Type: Regular Paper
Affiliations: Center for Health Research 3800 N. Interstate Ave. Portland, OR 97227-1098 U.S.A. E-mail: Mikel.Aickin@kp.org
Publication date: June 2000