Some adaptive Monte Carlo methods for Bayesian inference

Monte Carlo methods, in particular Markov chain Monte Carlo methods, have b ecome increasingly important as a tool for practical Bayesian inference in recent years. A wide range of algorithms is available, and choosing an algo rithm that will work well on a specific problem is challenging. It is there fore important to explore the possibility of developing adaptive strategies that choose and adjust the algorithm to a particular context based on info rmation obtained during sampling as well as information provided with the p roblem. This paper outlines some of the issues in developing adaptive metho ds and presents some preliminary results. Copyright (C) 1999 John Wiley & S ons, Ltd.