Scholion.ai

On the Representation of Ignorance

C. Villegas

Journal of the American Statistical Association · 1977 · Volume 72 · Issue 359

DOI: 10.1080/01621459.1977.10480629

Abstract

An invariance principle is used to show that λ −1 is the prior density representing ignorance concerning the parameter λ of a Poisson process, and a compatibility principle is applied to find an ignorance prior for the probabilities p i of the categories in a multinomial model. It is shown that II p i −1 is the only positive and exchangeable prior that satisfies the compatibility condition.

Enable JavaScript for citation tools and additional paper interactions.