Analysis of family-wise error rates in statistical parametric mapping using random field theory

TL;DR

This paper re-examines the family-wise error rates in statistical parametric mapping using random field theory, affirming the validity of parametric assumptions in neuroimaging data analysis despite recent critiques.

Contribution

It clarifies the implications of a previous critique on family-wise error rates, supporting the continued use of parametric methods in neuroimaging.

Findings

Parametric assumptions remain valid for neuroimaging analysis.

Random field theory supports family-wise error control.

Reassessment of previous critique affirms current methods.

Abstract

This technical report revisits the analysis of family-wise error rates in statistical parametric mapping - using random field theory - reported in (Eklund et al., 2015). Contrary to the understandable spin that these sorts of analyses attract, a review of their results suggests that they endorse the use of parametric assumptions - and random field theory - in the analysis of functional neuroimaging data. We briefly rehearse the advantages parametric analyses offer over nonparametric alternatives and then unpack the implications of (Eklund et al., 2015) for parametric procedures.