Avoiding non-independence in fMRI data analysis: Leave one subject out

Concerns regarding certain fMRI data analysis practices have recently evoked lively debate. The principal concern regards the issue of non-independence, in which an initial statistical test is followed by further non-independent statistical tests. In this report, we propose a simple, practical solution to reduce bias in secondary tests due to non-independence using a leave-one-subject-out (LOSO) approach. We provide examples of this method, show how it reduces effect size inflation, and suggest that it can serve as a functional localizer when within-subject methods are impractical.