A note on posterior sampling from Dirichlet mixture models
نویسنده
چکیده
In this note we observe that the recent MCMC methods of Papaspiliopoulos & Roberts (2008) and Walker (2007) for Dirichlet mixture models are intrinsically connected and can be naturally combined to yield an algorithm which is better (in terms of mixing), faster (in terms of execution time) and easier (in terms of implementation and coding) than either of them. Some keywords: Retrospective sampling; Slice sampling; Augmentation schemes; Label switching; ; Stick-breaking priors; blocking strategies
منابع مشابه
Hyperparameter estimation in Dirichlet process mixture models
In Bayesian density estimation and prediction using Dirichlet process mixtures of standard, exponential family distributions, the precision or total mass parameter of the mixing Dirichlet process is a critical hyperparameter that strongly influences resulting inferences about numbers of mixture components. This note shows how, with respect to a flexible class of prior distributions for this par...
متن کاملSampling from Dirichlet process mixture models with unknown concentration parameter: mixing issues in large data implementations
We consider the question of Markov chain Monte Carlo sampling from a general stick-breaking Dirichlet process mixture model, with concentration parameter [Formula: see text]. This paper introduces a Gibbs sampling algorithm that combines the slice sampling approach of Walker (Communications in Statistics - Simulation and Computation 36:45-54, 2007) and the retrospective sampling approach of Pap...
متن کاملGeneralized Weighted Chinese Restaurant Processes for Species Sampling Mixture Models
The class of species sampling mixture models is introduced as an extension of semiparametric models based on the Dirichlet process to models based on the general class of species sampling priors, or equivalently the class of all exchangeable urn distributions. Using Fubini calculus in conjunction with Pitman (1995, 1996), we derive characterizations of the posterior distribution in terms of a p...
متن کاملSlice Sampling σ -Stable Poisson-Kingman Mixture Models
The article is concerned with the use of Markov chain Monte Carlo methods for posterior sampling in Bayesian nonparametric mixture models. In particular, we consider the problem of slice sampling mixture models for a large class of mixing measures generalizing the celebrated Dirichlet process. Such a class of measures, known in the literature as σ -stable Poisson-Kingman models, includes as spe...
متن کاملA Note on the Dirichlet Process Prior in BayesianNonparametric Inference with Partial Exchangeability 1
We consider Bayesian nonparametric inference using a product of Dirichlet processes as the prior, when the data are continuous and partially exchangeable with an unknown partition. This includes change point problems and mixture models. We show that the discreteness of the Dirichlet process prior can have a large e ect on inference (posterior distributions and Bayes factors), leading to conclus...
متن کامل