Robust MCMC Methods for Spatial GLMM's

Ole F. Christensen, Gareth O. Roberts and Martin Sköld


Centre for Mathematical Sciences
Mathematical Statistics
Lund Institute of Technology,
Lund University,
2003

ISSN 1403-9338
Abstract:
Using Markov chain Monte Carlo methods for statistical inference is in practice often troublesome, since performance of the algorithm may hugely depend on the observed data, and what works well for one data-set can
fail miserably for another. In this paper, for spatial generalised linear mixed models, we discuss problems with algorithms previously used, and we construct an algorithm with robust mixing and convergence characteristics,
independent of the data. The strategy we have used for this construction is not model specific and could be applied in a much wider context.
Key words:
Markov chain Monte Carlo, parameterisation, spatial generalised linear mixed model, spatial statistics