Logo image
Back
Honest Importance Sampling With Multiple Markov Chains
Journal article   Peer reviewed

Honest Importance Sampling With Multiple Markov Chains

Aixin Tan, Hani Doss and James P Hobert
Journal of computational and graphical statistics, Vol.24(3), pp.792-826
07/03/2015
DOI: 10.1080/10618600.2014.929523
PMCID: PMC5502833
PMID: 28701855

View Online

Abstract

Importance sampling is a classical Monte Carlo technique in which a random sample from one probability density, pi(1), is used to estimate an expectation with respect to another, pi. The importance sampling estimator is strongly consistent and, as long as two simple moment conditions are satisfied, it obeys a central limit theorem (CLT). Moreover, there is a simple consistent estimator for the asymptotic variance in the CLT, which makes for routine computation of standard errors. Importance sampling can also be used in the Markov chain Monte Carlo (MCMC) context. Indeed, if the random sample from pi(1) is replaced by a Harris ergodic Markov chain with invariant density pi(1), then the resulting estimator remains strongly consistent. There is a price to be paid, however, as the computation of standard errors becomes more complicated. First, the two simple moment conditions that guarantee a CLT in the iid case are not enough in the MCMC context. Second, even when a CLT does hold, the asymptotic variance has a complex form and is difficult to estimate consistently. In this article, we explain how to use regenerative simulation to overcome these problems. Actually, we consider a more general setup, where we assume that Markov chain samples from several probability densities, pi(1), horizontal ellipsis , pi(k), are available. We construct multiple-chain importance sampling estimators for which we obtain a CLT based on regeneration. We show that if the Markov chains converge to their respective target distributions at a geometric rate, then under moment conditions similar to those required in the iid case, the MCMC-based importance sampling estimator obeys a CLT. Furthermore, because the CLT is based on a regenerative process, there is a simple consistent estimator of the asymptotic variance. We illustrate the method with two applications in Bayesian sensitivity analysis. The first concerns one-way random effect models under different priors. The second involves Bayesian variable selection in linear regression, and for this application, importance sampling based on multiple chains enables an empirical Bayes approach to variable selection.
 Mathematics Physical Sciences Science & Technology Statistics & Probability

Details

Metrics

10 Record Views
4 Times Cited - Web of Science
Logo image