Back to Search Start Over

Scalable Bayesian nonparametric measures for exploring pairwise dependence via Dirichlet Process Mixtures.

Authors :
Filippi S
Holmes CC
Nieto-Barajas LE
Source :
Electronic journal of statistics [Electron J Stat] 2016 Nov 16; Vol. 10 (2), pp. 3338-3354.
Publication Year :
2016

Abstract

In this article we propose novel Bayesian nonparametric methods using Dirichlet Process Mixture (DPM) models for detecting pairwise dependence between random variables while accounting for uncertainty in the form of the underlying distributions. A key criteria is that the procedures should scale to large data sets. In this regard we find that the formal calculation of the Bayes factor for a dependent-vs.-independent DPM joint probability measure is not feasible computationally. To address this we present Bayesian diagnostic measures for characterising evidence against a "null model" of pairwise independence. In simulation studies, as well as for a real data analysis, we show that our approach provides a useful tool for the exploratory nonparametric Bayesian analysis of large multivariate data sets.

Details

Language :
English
ISSN :
1935-7524
Volume :
10
Issue :
2
Database :
MEDLINE
Journal :
Electronic journal of statistics
Publication Type :
Academic Journal
Accession number :
29707100
Full Text :
https://doi.org/10.1214/16-ejs1171