AUTHOR:  McKeague, I. W. and Wefelmeyer, W.
DATE: 1996
TITLE: Markov Chain Monte Carlo and Rao--Blackwellization

ABSTRACT:
We introduce a form  of Rao--Blackwellization for Markov chains which uses
the transition distribution for conditioning. We show that for reversible
Markov chains, this form of Rao-Blackwellization always reduces
the asymptotic variance, and derive two explicit forms of
the variance reduction obtained through repeated Rao--Blackwellization.
The result applies to many Markov chain Monte Carlo methods used in practice.
In particular, we discuss an application to data augmentation
and give some simulation results for Ising model samplers.