Bayesian Graph-structured Variable Selection

Please join the GW Department of Statistics for a seminar with Mahlet G. Tadesse, professor and chair of the Department of Mathematics and Statistics at Georgetown University.

Abstract:
A graph structure is commonly used to characterize the dependence between variables, which may be induced by time, space, biological networks or other factors. Incorporating this dependence structure into the variable selection process can increase the power to detect subtle effects without increasing the probability of false discoveries and can improve the predictive performance. In this talk, I will present methods we have proposed to accomplish this in the context of spike-and-slab priors as well as global-local shrinkage priors. For the former, we specify a binary Markov random field prior that leverages evidence from correlated outcomes on the variable selection indicators to identify outcome-specific covariates. For the latter, we combine a Gaussian Markov random field prior with a horseshoe prior to perform selection on graph-structured variables. We illustrate the methods using epigenomic, genomic and transcriptomic data.

About the Speaker:
Mahlet Tadesse is professor and chair in the Department of Mathematics and Statistics at Georgetown University. Her research focuses on the development of statistical and computational tools for the analysis of large-scale genomic data. She is particularly interested in stochastic search methods and Bayesian inferential strategies to identify structures and relationships in high-dimensional data sets. She is an elected member of the International Statistical Institute and an elected fellow of the American Statistical Association.