Rank-normalization, folding, and localization: An improved R-hat for assessing convergence of MCMC

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2021-06

Major/Subject

Mcode

Degree programme

Language

en

Pages

28

Series

Bayesian Analysis

Abstract

Markov chain Monte Carlo is a key computational tool in Bayesian statistics, but it can be challenging to monitor the convergence of an iterative stochastic algorithm. In this paper we show that the convergence diagnostic R of Gelman and Rubin (1992) has serious flaws. Traditional R will fail to correctly diagnose convergence failures when the chain has a heavy tail or when the variance varies across the chains. In this paper we propose an alternative rank-based diagnostic that fixes these problems. We also introduce a collection of quantile-based local efficiency measures, along with a practical approach for computing Monte Carlo error estimates for quantiles. We suggest that common trace plots should be replaced with rank plots from multiple chains. Finally, we give recommendations for how these methods should be used in practice.

Description

Keywords

Other note

Citation

Vehtari, A, Gelman, A, Simpson, D, Carpenter, B & Burkner, P-C 2021, ' Rank-normalization, folding, and localization: An improved R-hat for assessing convergence of MCMC ', Bayesian Analysis, vol. 16, no. 2, pp. 667-718 . https://doi.org/10.1214/20-BA1221