Posterior Predictive Assessment of Model

This paper considers the Bayesian counterparts of the classical tests for goodness of t and their use in judging the t of a single Bayesian model to the observed data. We focus on posterior predictive assessment, in a framework that also includes conditioning on ancillary statistics. The Bayesian formulation facilitates the construction and calculation of a meaningful reference distribution not only for any (classical) statistic, but also for any parameter-dependent \statistic" or discrepancy variable. The latter allows us to propose the realized discrepancy assessment of model tness, which directly measures the true discrepancy between data and the posited model, for any aspect of the model which we want to explore. The computation required for the realized discrepancy assessment is a straightforward byproduct of the posterior simulation used for the original Bayesian analysis. We illustrate with three applied examples. The rst example, which serves mainly to motivate the work, illustrates the diiculty of classical tests in assessing the tness of a Poisson model to a positron emission tomography image that is constrained to be nonnegative. The second and third examples illustrate the details of the posterior predictive approach in two problems: estimation in a model with inequality constraints on the parameters, and estimation in a mixture model. In all three examples, standard test statistics (either a 2 or a likelihood ratio) are not pivotal: the diiculty is not just how to compute the reference distribution for the test, but that in the classical framework no such distribution exists, independent of the unknown model parameters.