Home > Research > Publications & Outputs > A case study in non-centering for data augmenta...


Text available via DOI:

View graph of relations

A case study in non-centering for data augmentation: stochastic epidemics

Research output: Contribution to journalJournal articlepeer-review

<mark>Journal publication date</mark>2005
<mark>Journal</mark>Statistics and Computing
Issue number4
Number of pages13
Pages (from-to)315-327
Publication StatusPublished
<mark>Original language</mark>English


In this paper, we introduce non-centered and partially non-centered MCMC algorithms for stochastic epidemic models. Centered algorithms previously considered in the literature perform adequately well for small data sets. However, due to the high dependence inherent in the models between the missing data and the parameters, the performance of the centered algorithms gets appreciably worse when larger data sets are considered. Therefore non-centered and partially non-centered algorithms are introduced and are shown to out perform the existing centered algorithms.