Bayesian Repulsive Gaussian Mixture Model
Authors:
- 1 April 2019
- journal article
- research article
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 115 (529) , 187-203
Abstract
We develop a general class of Bayesian repulsive Gaussian mixture models that encourage well-separated clusters, aiming at reducing potentially redundant components produced by independent priors for locations (such as the Dirichlet process). The asymptotic results for the posterior distribution of the proposed models are derived, including posterior consistency and posterior contraction rate in the context of nonparametric density estimation. More importantly, we show that compared to the independent prior on the component centers, the repulsive prior introduces additional shrinkage effect on the tail probability of the posterior number of components, which serves as a measurement of the model complexity. In addition, a generalized urn model that allows a random number of components and correlated component centers is developed based on the exchangeable partition distribution, which gives rise to the corresponding blocked-collapsed Gibbs sampler for posterior inference. We evaluate the performance and demonstrate the advantages of the proposed methodology through extensive simulation studies and real data analysis.Keywords
All Related Versions
Funding Information
- Hopkins inHealth
This publication has 28 references indexed in Scilit:
- Mixture Models With a Prior on the Number of ComponentsJournal of the American Statistical Association, 2017
- Maximum Lq-Likelihood Estimation via the Expectation-Maximization Algorithm: A Robust Estimation of Mixture ModelsJournal of the American Statistical Association, 2013
- The -consistency of Dirichlet mixtures in multivariate Bayesian density estimationJournal of Multivariate Analysis, 2010
- Sampling the Dirichlet Mixture Model with SlicesCommunications in Statistics - Simulation and Computation, 2007
- Model-Based Clustering for Expression Data via a Dirichlet Process Mixture Model2006
- Markov Chain Sampling Methods for Dirichlet Process Mixture ModelsJournal of Computational and Graphical Statistics, 2000
- Robustness Properties ofkMeans and TrimmedkMeansJournal of the American Statistical Association, 1999
- Estimating Mixture of Dirichlet Process ModelsJournal of Computational and Graphical Statistics, 1998
- Density Estimation for Statistics and Data Analysis1986
- On Bayes proceduresProbability Theory and Related Fields, 1965