Nonparametric Bayes inference on conditional independence

DOI10.1093/BIOMET/ASV060MaRDI QIDQ2797330zbMATH OpenOpenAlexFDO

Authors T. Kunihama, David Dunson

Publication date 5 April 2016

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1404.1429

zbMATH Keywords

criminology dataDirichlet processempirical processgraphical modelmutual informationvariable selection

Mathematics Subject Classification ID

Empirical decision procedures; empirical Bayes procedures (62C12) Nonparametric estimation (62G05) Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20) Applications of statistics (62P99)

Abstract: In broad applications, it is routinely of interest to assess whether there is evidence in the data to refute the assumption of conditional independence of $Y$ and $X$ conditionally on $Z$. Such tests are well developed in parametric models but are not straightforward in the nonparametric case. We propose a general Bayesian approach, which relies on an encompassing nonparametric Bayes model for the joint distribution of $Y$, $X$ and $Z$. The framework allows $Y$, $X$ and $Z$ to be random variables on arbitrary spaces, and can accommodate different dimensional vectors having a mixture of discrete and continuous measurement scales. Using conditional mutual information as a scalar summary of the strength of the conditional dependence relationship, we construct null and alternative hypotheses. We provide conditions under which the correct hypothesis will be consistently selected. Computational methods are developed, which can be incorporated within MCMC algorithms for the encompassing model. The methods are applied to variable selection and assessed through simulations and criminology applications.

Recommendations

• A simple measure of conditional dependence
• Bayesian nonparametric tests via sliced inverse modeling
• A Bayesian nonparametric approach to testing for dependence between random variables
• Strongly consistent nonparametric tests of conditional independence
• Nonparametric Bayes conditional distribution modeling with variable selection

Cited in

(10)

• Independence and Bayesian updating methods
• Bayesian nonparametric tests via sliced inverse modeling
• A Bayesian nonparametric approach to testing for dependence between random variables
• Exploring dependence between categorical variables: benefits and limitations of using variable selection within Bayesian clustering in relation to log-linear modelling with interaction terms
• Nonparametric Bayes conditional distribution modeling with variable selection
• Bayesian inference with dependent normalized completely random measures
• Symbolic and Quantitative Approaches to Reasoning with Uncertainty
• Nonconglomerative coherent conditional probabilities in statistical inference
• Semiparametric Bayes instrumental variable estimation with many weak instruments
• Bayesian mixture modeling for multivariate conditional distributions

This page was built for publication: Nonparametric Bayes inference on conditional independence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2797330)