Robust Markov chain Monte Carlo methods for spatial generalized linear mixed models
(2006) In Journal of Computational and Graphical Statistics 15(1). p.1-17- 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.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/416473
- author
- Christensen, OF ; Roberts, GO and Sköld, Martin LU
- organization
- publishing date
- 2006
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- parameterization, spatial statistics
- in
- Journal of Computational and Graphical Statistics
- volume
- 15
- issue
- 1
- pages
- 1 - 17
- publisher
- American Statistical Association
- external identifiers
-
- wos:000235953700001
- scopus:33645558077
- ISSN
- 1537-2715
- DOI
- 10.1198/106186006X100470
- language
- English
- LU publication?
- yes
- id
- bbf261ed-be69-446b-a8ab-06b3bfe8292e (old id 416473)
- date added to LUP
- 2016-04-01 12:22:20
- date last changed
- 2022-04-13 18:06:22
@article{bbf261ed-be69-446b-a8ab-06b3bfe8292e, 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.}}, author = {{Christensen, OF and Roberts, GO and Sköld, Martin}}, issn = {{1537-2715}}, keywords = {{parameterization; spatial statistics}}, language = {{eng}}, number = {{1}}, pages = {{1--17}}, publisher = {{American Statistical Association}}, series = {{Journal of Computational and Graphical Statistics}}, title = {{Robust Markov chain Monte Carlo methods for spatial generalized linear mixed models}}, url = {{http://dx.doi.org/10.1198/106186006X100470}}, doi = {{10.1198/106186006X100470}}, volume = {{15}}, year = {{2006}}, }