Discussion of James O. Berger and Luis R. Pericchi, "Objective Bayesian Methods for Model Selection: Introduction and Comparison"
J. K. Ghosh, Tapas Samanta · Lecture notes-monograph series · 2001
A number of objective Bayesian methods of model selection and testing a sharp null hypothesis have been proposed and developed to deal with the difficulties with improper noninformative priors.Professors Berger and Pericchi have been the leading contributors to this area.Their present work is an illuminating overview of the subject as it stands now.As part of the overview they take up the important problem of evaluating these methods and give some final recommendations.We generally agree with them but feel many points need further study.