On MCMC sampling in hierarchical longitudinal models

Authors:
Siddhartha Chib;Bradley P. Carlin
Affiliations:
John M. Olin School of Business, Washington University, One Brookings Drive, St. Louis, Missouri 63130, USA;Division of Biostatistics, School of Public Health, University of Minnesota, Box 303 Mayo Building, Minneapolis, Minnesota 55455, USA
Venue:
Statistics and Computing
Year:
1999

Citing 0
Cited 10

Conditional simulation from highly structured Gaussian systems, with application to blocking-MCMC for the Bayesian analysis of very large linear models

Statistics and Computing
Slice sampling for simulation based fitting of spatial data models

Statistics and Computing
Bayesian analysis of the unobserved ARCH model

Statistics and Computing
Market Roll-Out and Retailer Adoption for New Brands

Marketing Science
Bayesian analysis of two dependent 2×2 contingency tables

Computational Statistics & Data Analysis
Efficient parallelisation of Metropolis-Hastings algorithms using a prefetching approach

Computational Statistics & Data Analysis
A space-time filter for panel data models containing random effects

Computational Statistics & Data Analysis
Parallel multivariate slice sampling

Statistics and Computing
Bayesian analysis of multivariate t linear mixed models using a combination of IBF and Gibbs samplers

Journal of Multivariate Analysis
A Bayesian model for longitudinal circular data based on the projected normal distribution

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Markov chain Monte Carlo (MCMC) algorithms have revolutionized Bayesian practice. In their simplest form (i.e., when parameters are updated one at a time) they are, however, often slow to converge when applied to high-dimensional statistical models. A remedy for this problem is to block the parameters into groups, which are then updated simultaneously using either a Gibbs or Metropolis-Hastings step. In this paper we construct several (partially and fully blocked) MCMC algorithms for minimizing the autocorrelation in MCMC samples arising from important classes of longitudinal data models. We exploit an identity used by Chib (1995) in the context of Bayes factor computation to show how the parameters in a general linear mixed model may be updated in a single block, improving convergence and producing essentially independent draws from the posterior of the parameters of interest. We also investigate the value of blocking in non-Gaussian mixed models, as well as in a class of binary response data longitudinal models. We illustrate the approaches in detail with three real-data examples.