Geometric ergodicity of trans-dimensional Markov chain Monte Carlo algorithms

This article studies the convergence properties of trans-dimensional MCMC algorithms when the total number of models is finite. It is shown that, for reversible and some non-reversible trans-dimensional Markov chains, under mild conditions, geometric convergence is guaranteed if the Markov chains associated with the within-model moves are geometrically ergodic. This result is proved in an $L^2$ framework using the technique of Markov chain decomposition. While the technique was previously developed for reversible chains, this work extends it to the point that it can be applied to some commonly used non-reversible chains. Under geometric convergence, a central limit theorem holds for ergodic averages, even in the absence of Harris ergodicity. This allows for the construction of simultaneous confidence intervals for features of the target distribution. This procedure is rigorously examined in a trans-dimensional setting, and special attention is given to the case where the asymptotic covariance matrix in the central limit theorem is singular. The theory and methodology herein are applied to reversible jump algorithms for two Bayesian models: a robust autoregression with unknown model order, and a probit regression with variable selection.