Flexible Multivariate Bayesian Variable Selection: Application to DNA Methylation Induced by Air Pollution

• Activity Number: 543
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Kyu Ha Lee* and Mahlet Tadesse and Brent Coull
• Companies: Harvard School of Public Health and Georgetown University and Harvard University
• Keywords: Bayesian variable selection ; Gibbs sampler ; Markov chain Monte Carlo ; multivariate regression

Abstract

The analysis of multiple outcomes is becoming increasingly common in modern biomedical studies. Existing frequentist and Bayesian variable selection approaches rely on strategies that use information on the mean vector of the multivariate outcomes. In this work we propose a variable selection approach for multivariate normal responses incorporating not only information on the mean model, but also information on the variance-covariance matrix of the outcomes. The approach effectively leverages evidence from all correlated outcomes to estimate the effect of a particular covariate on a given outcome. To implement this strategy, we develop a Bayesian variable selection method that builds a multivariate prior for the variable selection indicators based on the variance-covariance parameters in the model. We show both via simulation and through application of the approach to epigenetic data from the Normative Aging Study that the proposed variable selection strategy can boost the power to detect subtle effects without increasing the probability of false discoveries for covariates having null effects on the outcomes.