AN APPROACH TO BAYESIAN SENSITIVITY ANALYSIS

This paper describes an approach to Bayesian sensitivity analysis that uses an influence statistic and an outlier statistic to assess the se nsitivity of a model to perturbations. The basic outlier statistic is a Bayes factor, whereas the influence statistic depends strongly on th e purpose of the analysis. The task of influence analysis is aided by having an interpretable influence statistic. Two alternative divergenc es, an L(1)-distance and a chi(2)-divergence, are proposed and shown t o be interpretable. The Bayes factor and the proposed influence measur es are shown to be summaries of the posterior of a perturbation functi on.