Robust Markov chain Monte Carlo methods for spatial generalized linear mixed models

Research output: Contribution to journalArticle

Abstract

Using Markov chain Monte Carlo methods for statistical inference is often troublesome in practice, because performance of the algorithm may hugely depend on the observed data, and what works well for one dataset may fail miserably for another. In this article, for spatial generalized linear mixed models (GLMMs), 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.

Details

Authors
  • OF Christensen
  • GO Roberts
  • Martin Sköld
Organisations
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • Probability Theory and Statistics

Keywords

  • parameterization, spatial statistics
Original languageEnglish
Pages (from-to)1-17
JournalJournal of Computational and Graphical Statistics
Volume15
Issue number1
Publication statusPublished - 2006
Publication categoryResearch
Peer-reviewedYes