Two-sample Bayesian Nonparametric Hypothesis Testing
Abstract
In this article we describe Bayesian nonparametric procedures for two-sample hypothesis testing. Namely, given two sets of samples \stackrel{\scriptscriptstyle{iid}}{\s im} and \stackrel{\scriptscriptstyle{iid}}{\sim}, with unknown, we wish to evaluate the evidence for the null hypothesis versus the alternative . Our method is based upon a nonparametric P\'{o}lya tree prior centered either subjectively or using an empirical procedure. We show that the P\'{o}lya tree prior leads to an analytic expression for the marginal likelihood under the two hypotheses and hence an explicit measure of the probability of the null .
Keywords
Cite
@article{arxiv.0910.5060,
title = {Two-sample Bayesian Nonparametric Hypothesis Testing},
author = {Chris C. Holmes and François Caron and Jim E. Griffin and David A. Stephens},
journal= {arXiv preprint arXiv:0910.5060},
year = {2025}
}
Comments
Published at http://dx.doi.org/10.1214/14-BA914 in the Bayesian Analysis (http://projecteuclid.org/euclid.ba) by the International Society of Bayesian Analysis (http://bayesian.org/)