Nonsubjective priors via predictive relative entropy regret

We explore the construction of nonsubjective prior distributions in Bayesian statistics via a posterior predictive relative entropy regret criterion. We carry out a minimax analysis based on a derived asymptotic predictive loss function and show that this approach to prior construction has a number of attractive features. The approach here differs from previous work that uses either prior or posterior relative entropy regret in that we consider predictive performance in relation to alternative nondegenerate prior distributions. The theory is illustrated with an analysis of some specific examples.

[1]  H. Kuboki.  Reference priors for prediction , 1998 .

[2]  Jayanta K. Ghosh,et al.  Characterization of priors under which Bayesian and frequentist Barlett corrections are equivalent in the multiparameter case , 1991 .

[3]  J. Bernardo.  Reference Posterior Distributions for Bayesian Inference , 1979 .

[4]  F. Komaki.  On asymptotic properties of predictive distributions , 1996 .

[5]  J. Hartigan.  The maximum likelihood prior , 1998 .

[6]  Trevor J. Sweeting,et al.  Approximate Bayesian computation based on signed roots of log-density ratios (with discussion) , 1996 .

[7]  P. McCullagh.  Tensor Methods in Statistics , 1987 .

[8]  J. Aitchison.  Goodness of prediction fit , 1975 .

[9]  B. Clarkea,et al.  Partial information reference priors : derivation and interpretations , 2003 .

[10]  L. Tierney,et al.  The validity of posterior expansions based on Laplace''s method , 1990 .

[11]  R. Mukerjee,et al.  Probability Matching Priors: Higher Order Asymptotics , 2004 .

[12]  Purushottam W. Laud,et al.  Predictive Model Selection , 1995 .

[13]  Trevor J. Sweeting,et al.  Coverage probability bias, objective Bayes and the likelihood principle , 2001 .

[14]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[15]  H. Akaike.  A new look at the Bayes procedure , 1978 .

[16]  Tj Sweeting,et al.  Invited discussion of A. R. Barron: Information-theoretic characterization of Bayes performance and the choice of priors in parametric and nonparametric problems , 1998 .

[17]  Andrew R. Barron,et al.  Minimax redundancy for the class of memoryless sources , 1997, IEEE Trans. Inf. Theory.

[18]  Dongchu Sun,et al.  Reference priors with partial information , 1998 .

[19]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[20]  Andrew R. Barron,et al.  Information-theoretic asymptotics of Bayes methods , 1990, IEEE Trans. Inf. Theory.

[21]  Feng Liang,et al.  Exact minimax strategies for predictive density estimation, data compression, and model selection , 2002, IEEE Transactions on Information Theory.

[22]  A. Barron,et al.  Jeffreys' prior is asymptotically least favorable under entropy risk , 1994 .

[23]  R. Tibshirani.  Noninformative priors for one parameter of many , 1989 .

[24]  Trevor J. Sweeting,et al.  On the implementation of local probability matching priors for interest parameters , 2005 .

[25]  Malay Ghosh,et al.  Bayesian prediction with approximate frequentist validity , 2000 .