Markov Chain Sampling Methods for Dirichlet Process Mixture Models Export

@article{neal-2000a, abstract = {This article reviews Markov chain methods for sampling from the posterior distribution of a Dirichlet process mixture model and presents two new classes of methods. One new approach is to make Metropolis-Hastings updates of the indicators specifying which mixture component is associated with each observation, perhaps supplemented with a partial form of Gibbs sampling. The other new approach extends Gibbs sampling for these indicators by using a set of auxiliary parameters. These methods are simple to implement and are more efficient than previous ways of handling general Dirichlet process mixture models with non-conjugate priors.}, author = {Neal, Radford M.}, citeulike-article-id = {634913}, citeulike-linkout-0 = {http://dx.doi.org/10.2307/1390653}, citeulike-linkout-1 = {http://www.jstor.org/stable/1390653}, citeulike-linkout-2 = {http://www-clmc.usc.edu/~cs599_ct/neal-TR1998.pdf}, doi = {10.2307/1390653}, issn = {10618600}, journal = {Journal of Computational and Graphical Statistics}, keywords = {dirichlet-process, dirichlet-process-mixture, mcmc}, number = {2}, pages = {249--265}, posted-at = {2009-04-22 17:26:02}, priority = {2}, publisher = {American Statistical Association, Institute of Mathematical Statistics, and Interface Foundation of America}, title = {Markov Chain Sampling Methods for Dirichlet Process Mixture Models}, url = {http://dx.doi.org/10.2307/1390653}, volume = {9}, year = {2000} }

TY - JOUR ID - neal-2000a L3 - citeulike-article-id:634913 N2 - This article reviews Markov chain methods for sampling from the posterior distribution of a Dirichlet process mixture model and presents two new classes of methods. One new approach is to make Metropolis-Hastings updates of the indicators specifying which mixture component is associated with each observation, perhaps supplemented with a partial form of Gibbs sampling. The other new approach extends Gibbs sampling for these indicators by using a set of auxiliary parameters. These methods are simple to implement and are more efficient than previous ways of handling general Dirichlet process mixture models with non-conjugate priors. IS - 2 JF - Journal of Computational and Graphical Statistics SN - 10618600 EP - 265 TI - Markov Chain Sampling Methods for Dirichlet Process Mixture Models PB - American Statistical Association, Institute of Mathematical Statistics, and Interface Foundation of America VL - 9 SP - 249 KW - dirichlet-process KW - dirichlet-process-mixture KW - mcmc AU - Neal, Radford PY - 2000/// UR - http://dx.doi.org/10.2307/1390653 ER -