PLACE:  319 Snedecor

SPEAKER:
Dan Sargent
Mayo Clinic

TITLE:
Structured Markov Chain Monte Carlo

ABSTRACT:

In this paper we introduce a general method for Bayesian computing in
richly-parameterized models, Structured Markov Chain Monte Carlo (SMCMC), that
is based on a blocked hybrid of the Gibbs sampling and Metropolis-Hastings
algorithms.  SMCMC speeds algorithm convergence by using the structure that is
present in the problem to suggest an appropriate Metropolis-Hastings candidate
distribution.  While the approach is easiest to describe for hierarchical
normal linear models, we show that its extension to both non-normal and
nonlinear cases is straightforward.  After describing the method in detail we
compare its performance (in terms of runtime and autocorrelation in the
samples) to other existing methods, including the single-site updating Gibbs
sampler available in the popular BUGS software package.  Our results suggest
significant improvements in convergence for many problems using SMCMC, as well
as broad applicability of the method, including previously intractable
hierarchical nonlinear model settings.
 

KEY WORDS: Blocking; Convergence acceleration; Gibbs sampling; Hierarchical
model; Metropolis-Hastings algorithm.
 

COFFEE: 3:45 p.m., 104 Snedecor