An Automated Stopping Rule for MCMC Convergence Assessment - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 1998

An Automated Stopping Rule for MCMC Convergence Assessment

Jean Diebolt
  • Function : Author


In this paper, we propose a methodology essentially based on the Central Limit Theorem for Markov chains to monitor convergence of MCMC algorithms using actual outputs. Our methods are grounded on the fact that normality is a testable implication of sufficient mixing. The first control tool tests the normality hypothesis for normalized averages of functions of the Markov chain over independent parallel chains started from a dispersed distribution. A second connected tool is based on graphical monitoring of the stabilization of the variance after $n$ iterations near the limiting variance appearing in the CLT. Both methods work without knowledge on the sampler driving the chain, and the normality diagnostic leads to automated stopping rules. The methodology is developed for finite state Markov chains, and extended to the continuous case. Heuristic procedures based on Berry-Essée- n bounds are also investigated. These stopping rules are implemented in a software toolbox whose performances are illustrated through simulations for finite and continuous state chains reflecting some typical situations (slow mixing, multimodality) and a full scale application. Comparisons are made with the binary control method of Raftery and Lewis.
Fichier principal
Vignette du fichier
RR-3566.pdf (451.27 Ko) Télécharger le fichier

Dates and versions

inria-00073116 , version 1 (24-05-2006)


  • HAL Id : inria-00073116 , version 1


Didier Chauveau, Jean Diebolt. An Automated Stopping Rule for MCMC Convergence Assessment. RR-3566, INRIA. 1998. ⟨inria-00073116⟩
113 View
6659 Download


Gmail Facebook Twitter LinkedIn More