Asymptotically minimax Bayesian predictive densities for multinomial models

Abstract

One-step ahead prediction for the multinomial model is considered. The performance of a predictive density is evaluated by the average Kullback-Leibler divergence from the true density to the predictive density. Asymptotic approximations of risk functions of Bayesian predictive densities based on Dirichlet priors are obtained. It is shown that a Bayesian predictive density based on a specific Dirichlet prior is asymptotically minimax. The asymptotically minimax prior is different from known objective priors such as the Jeffreys prior or the uniform prior.

Cited by in corpus (6)

• Bayesian Point Estimation and Predictive Density Estimation for the Binomial Distribution with a Restricted Probability Parameter
• Bayesian Estimation for the Multivariate Hypergeometric Distribution Incorporating Information from Aggregated Observations
• Bayesian Estimation of Multinomial Cell Probabilities Incorporating Information from Aggregated Observations
• Bayesian Shrinkage Estimation for Stratified Count Data
• Bayesian Shrinkage Approaches to Unbalanced Problems of Estimation and Prediction on the Basis of Negative Multinomial Samples
• Relations Between the Conditional Normalized Maximum Likelihood Distributions and the Latent Information Priors