Spatial Bayesian Variable Selection and Grouping in High-Dimensional Covariate Spaces with Application to fMRI

• Activity Number: 25
• Type: Topic Contributed
• Date/Time: Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
• Sponsor: ENAR
• Author(s): Tingting Zhang*+
• Companies: University of Virginia
• Keywords: Bayesian ; Dirichlet process ; fMRI ; Ising model ; Phase transition ; variable selection

Abstract

Multi-subject fMRI data provide opportunities to study population-wide relationship between human brain activity and individual biological or behavioral traits. But statistical modeling, analysis and computation for such massive and noisy data with a complicated spatio-temporal correlation structure is extremely challenging. In this article, within the framework of Bayesian stochastic search variable selection, we propose a joint Ising and Dirichlet Process (Ising-DP) prior to achieve selection of spatially correlated brain voxels that are predictive of individual responses. The Ising component of the prior utilizes of the spatial information between voxels, and the DP component groups the coefficients of the large number of voxels to a small set of values and thus greatly reduces the posterior computational burden. To address the phase transition phenomenon of the Ising prior, we propose a new analytic approach to derive bounds for the hyperparameters, illustrated on 2- and 3-dimensional lattices. The proposed method is compared with several alternative methods via simulations, and is applied to the fMRI data collected from the Kliff hand-holding experiment.