An analytic example of latent information prior

Abstract

Recently Komaki proposed latent information priors as an objective prior. In this short article, we consider the one-step ahead prediction based on one-sample under the binomial model. In this specific case, the latent information prior is derived analytically and shown to be a discrete prior. It verifies the numerical result by Komaki. As a by-product, we obtain the minimal complete class, the minimax predictive distribution.

8 pages