Dynamics of Bayesian Updating with Dependent Data and Misspecified Models

Cosma Shalizi


Recent work on the convergence of posterior distributions under Bayesian updating has established conditions under which the posterior will concentrate on the truth, if the latter has a perfect representation within the support of the prior, and under various dynamical assumptions, such as the data being independent and identically distributed or Markovian. Here I establish sufficient conditions for the convergence of the posterior distribution in non-parametric problems even when all of the hypotheses are wrong, and the data-generating process has a complicated dependence structure. The main dynamical assumption is the generalized asymptotic equipartition (or "Shannon-McMillan-Breiman") property of information theory. I derive a kind of large deviations principle for the posterior measure, and discuss the advantages of predicting using a combination of models known to be wrong. An appendix sketches connections between the present results and the "replicator dynamics" of evolutionary theory.

Heidi Sestrich 2009-02-06
Here is the full PDF text for this technical report. It is 401018 bytes long.