Dirichlet Process Mixture Models with Shrinkage Prior
Preprint
Abstract
We propose Dirichlet Process Mixture (DPM) models for prediction and cluster-wise variable selection, based on two choices of shrinkage baseline prior distributions for the linear regression coefficients, namely the Horseshoe prior and Normal-Gamma prior. We show in a simulation study that each of the two proposed DPM models tend to outperform the standard DPM model based on the non-shrinkage normal prior, in terms of predictive, variable selection, and clustering accuracy. This is especially true for the Horseshoe model, and when the number of covariates exceeds the within-cluster sample size. A real data set is analyzed to illustrate the proposed modeling methodology, where both proposed DPM models again attained better predictive accuracy.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Optimal Bayesian estimators for latent variable cluster modelsStatistics and Computing, 2017
- A comparative review of variable selection techniques for covariate dependent Dirichlet process mixture modelsCanadian Journal of Statistics, 2017
- A Novel Machine Learning Model for Estimation of Sale Prices of Real Estate UnitsJournal of Construction Engineering and Management, 2016
- A Simple Sampler for the Horseshoe EstimatorIEEE Signal Processing Letters, 2015
- Variable selection in covariate dependent random partition models: an application to urinary tract infectionStatistics in Medicine, 2015
- Bayesian nonparametric mixed random utility modelsComputational Statistics & Data Analysis, 2012
- Regression Shrinkage and Selection via The Lasso: A RetrospectiveJournal of the Royal Statistical Society Series B: Statistical Methodology, 2011
- The horseshoe estimator for sparse signalsBiometrika, 2010
- Regression Shrinkage and Selection Via the LassoJournal of the Royal Statistical Society Series B: Statistical Methodology, 1996
- Comparing partitionsJournal of Classification, 1985