Open Access
Translator Disclaimer
December 2018 Bayesian Spatiotemporal Modeling Using Hierarchical Spatial Priors, with Applications to Functional Magnetic Resonance Imaging (with Discussion)
Martin Bezener, John Hughes, Galin Jones
Bayesian Anal. 13(4): 1261-1313 (December 2018). DOI: 10.1214/18-BA1108

Abstract

We propose a spatiotemporal Bayesian variable selection model for detecting activation in functional magnetic resonance imaging (fMRI) settings. Following recent research in this area, we use binary indicator variables for classifying active voxels. We assume that the spatial dependence in the images can be accommodated by applying an areal model to parcels of voxels. The use of parcellation and a spatial hierarchical prior (instead of the popular Ising prior) results in a posterior distribution amenable to exploration with an efficient Markov chain Monte Carlo (MCMC) algorithm. We study the properties of our approach by applying it to simulated data and an fMRI data set.

Citation

Download Citation

Martin Bezener. John Hughes. Galin Jones. "Bayesian Spatiotemporal Modeling Using Hierarchical Spatial Priors, with Applications to Functional Magnetic Resonance Imaging (with Discussion)." Bayesian Anal. 13 (4) 1261 - 1313, December 2018. https://doi.org/10.1214/18-BA1108

Information

Published: December 2018
First available in Project Euclid: 8 May 2018

zbMATH: 06989984
MathSciNet: MR3882358
Digital Object Identifier: 10.1214/18-BA1108

Keywords: areal model , Bayesian variable selection , fMRI , MCMC , Spatiotemporal

JOURNAL ARTICLE
53 PAGES


SHARE
Vol.13 • No. 4 • December 2018
Back to Top