Studying Convergence of Markov Chain Monte Carlo Algorithms Using Coupled Sample Paths

Abstract I describe a simple procedure for investigating the convergence properties of Markov chain Monte Carlo sampling schemes. The procedure uses coupled chains from the same sampler, obtained by using the same sequence of random deviates for each run. By examining the distribution of the iteration at which all sample paths couple, convergence properties for the system can be established. The procedure also provides a simple diagnostic for detecting modes in multimodal posteriors. Several examples of the procedure are provided. In Ising models, the relation between the correlation parameter and the convergence rate of rudimentary Gibbs samplers is investigated. In another example, the effects of multiple modes on the convergence of coupled paths are explored using mixtures of bivariate normal distributions. The technique is also used to evaluate the convergence properties of a Gibbs sampling scheme applied to a model for rat growth rates.

[1]  P. Odell,et al.  A Numerical Procedure to Generate a Sample Covariance Matrix , 1966 .

[2]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[3]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[4]  G. Milovanović.  ON SOME INTEGRAL INEQUALITIES , 1975 .

[5]  D. Griffeath.  A maximal coupling for Markov chains , 1975 .

[6]  J. Pitman.  On coupling of Markov chains , 1976 .

[7]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[9]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[10]  W. Wong,et al.  The calculation of posterior distributions by data augmentation , 1987 .

[11]  A. O'Hagan,et al.  The Calculation of Posterior Distributions by Data Augmentation: Comment , 1987 .

[12]  Adrian F. M. Smith,et al.  Bayesian computation via the gibbs sampler and related markov chain monte carlo methods (with discus , 1993 .

[13]  Julian Besag,et al.  Digital Image Processing: Towards Bayesian image analysis , 1989 .

[14]  William H. Press,et al.  Book-Review - Numerical Recipes in Pascal - the Art of Scientific Computing , 1989 .

[15]  Adrian F. M. Smith,et al.  Sampling-Based Approaches to Calculating Marginal Densities , 1990 .

[16]  S. E. Hills,et al.  Illustration of Bayesian Inference in Normal Data Models Using Gibbs Sampling , 1990 .

[17]  William H. Press,et al.  Numerical Recipes: FORTRAN , 1988 .

[18]  J. Besag,et al.  Bayesian image restoration, with two applications in spatial statistics , 1991 .

[19]  Josip Pečarić,et al.  Inequalities Involving Functions and Their Integrals and Derivatives , 1991 .

[20]  Charles J. Geyer,et al.  Practical Markov Chain Monte Carlo , 1992 .

[21]  T. Lindvall.  Lectures on the Coupling Method , 1992 .

[22]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[23]  M. Tanner,et al.  Facilitating the Gibbs Sampler: The Gibbs Stopper and the Griddy-Gibbs Sampler , 1992 .

[24]  C. Geyer,et al.  Constrained Monte Carlo Maximum Likelihood for Dependent Data , 1992 .

[25]  J. Besag,et al.  Spatial Statistics and Bayesian Computation , 1993 .

[26]  C. Hwang,et al.  Convergence rates of the Gibbs sampler, the Metropolis algorithm and other single-site updating dynamics , 1993 .

[27]  Julian Besag,et al.  Towards Bayesian image analysis , 1993 .

[28]  J. Rosenthal.  Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo , 1995 .

[29]  V. Johnson.  A Model for Segmentation and Analysis of Noisy Images , 1994 .

[30]  L. Tierney.  Markov Chains for Exploring Posterior Distributions , 1994 .

[31]  Richard L. Tweedie,et al.  Geometric Convergence Rates for Stochastically Ordered Markov Chains , 1996, Math. Oper. Res..

[32]  Joong-Kweon Sohn,et al.  Convergence Diagnostics for the Gibbs Sampler , 1996 .