Modeling with Normalized Random Measure Mixture Models

Abstract

The Dirichlet process mixture model and more general mixtures based on discrete random probability measures have been shown to be flexible and accurate models for density estimation and clustering. The goal of this paper is to illustrate the use of normalized random measures as mixing measures in nonparametric hierarchical mixture models and point out how possible computational issues can be successfully addressed. To this end, we first provide a concise and accessible introduction to normalized random measures with independent increments. Then, we explain in detail a particular way of sampling from the posterior using the Ferguson-Klass representation. We develop a thorough comparative analysis for location-scale mixtures that considers a set of alternatives for the mixture kernel and for the nonparametric component. Simulation results indicate that normalized random measure mixtures potentially represent a valid default choice for density estimation problems. As a byproduct of this study an R package to fit these models was produced and is available in the Comprehensive R Archive Network (CRAN).

Published in at http://dx.doi.org/10.1214/13-STS416 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (2)

• MCMC for Normalized Random Measure Mixture Models
• Bayesian inference with dependent normalized completely random measures

Cited by in corpus (7)

• MCMC for Normalized Random Measure Mixture Models
• Full Bayesian inference with hazard mixture models
• A moment-matching Ferguson and Klass algorithm
• A marginal sampler for $\sigma$-Stable Poisson-Kingman mixture models
• A unified construction for series representations and finite approximations of completely random measures
• Nonparametric priors with full-range borrowing of information
• Principled Estimation and Prediction with Competing Risks: a Bayesian Nonparametric Approach