Convergence complexity analysis of Albert and Chib's algorithm for Bayesian probit regression
Abstract
The use of MCMC algorithms in high dimensional Bayesian problems has become routine. This has spurred so-called convergence complexity analysis, the goal of which is to ascertain how the convergence rate of a Monte Carlo Markov chain scales with sample size, , and/or number of covariates, . This article provides a thorough convergence complexity analysis of Albert and Chib's (1993) data augmentation algorithm for the Bayesian probit regression model. The main tools used in this analysis are drift and minorization conditions. The usual pitfalls associated with this type of analysis are avoided by utilizing centered drift functions, which are minimized in high posterior probability regions, and by using a new technique to suppress high-dimensionality in the construction of minorization conditions. The main result is that the geometric convergence rate of the underlying Markov chain is bounded below 1 both as (with fixed), and as (with fixed). Furthermore, the first computable bounds on the total variation distance to stationarity are byproducts of the asymptotic analysis.
Cite
@article{arxiv.1712.08867,
title = {Convergence complexity analysis of Albert and Chib's algorithm for Bayesian probit regression},
author = {Qian Qin and James P. Hobert},
journal= {arXiv preprint arXiv:1712.08867},
year = {2018}
}
Comments
This is a revised version of the article "Asymptotically stable drift and minorization for Markov chains with application to Albert and Chib's algorithm"