Modeling and inference of multisubject fMRI data

This article reviews four commonly used approaches to group modeling in fMRI. The methods differ in their computational intensity (FSL with its two-level estimation including MCM being the most intense) and assumptions (SPM2 with its assumption of spatially homogeneous covariance V_g being most restrictive). This study also distinguishes fixed-effects models from mixed-effects models and motivates the importance of a mixed-effects model for group fMRI analysis. The sections following that describe single-subject modeling and show a general method for estimating the group model.