摘要：The inferential problem of associating data to mixture components is dif-
cult when components are nearby or overlapping. We introduce a new split-merge
Markov chain Monte Carlo technique that eciently classi es observations by splitting
and merging mixture components of a nonconjugate Dirichlet process mixture model.
Our method, which is a Metropolis-Hastings procedure with split-merge proposals, samples
clusters of observations simultaneously rather than incrementally assigning observations
to mixture components. Split-merge moves are produced by exploiting properties
of a restricted Gibbs sampling scan. A simulation study compares the new split-merge
technique to a nonconjugate version of Gibbs sampling and an incremental Metropolis-
Hastings technique. The results demonstrate the improved performance of the new
sampler.
关键词：Bayesian model, Markov chain Monte Carlo, split-merge moves, nonconjugate prior
