How to improve parameter estimates in GLM-based fMRI data analysis: cross-validated Bayesian model averaging

• Published in: NeuroImage (Orlando, Fla.) Vol. 158; pp. 186 - 195
• Main Authors: Soch, Joram, Meyer, Achim Pascal, Haynes, John-Dylan, Allefeld, Carsten
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.09.2017; Elsevier Limited
• Subjects: Algorithms; Bayes Theorem; Bayesian analysis; Bayesian model averaging; Brain Mapping - methods; correlated regressors; cross-validation; Data analysis; Data processing; Economic models; fMRI-based neuroimaging; Functional magnetic resonance imaging; Humans; Image Processing, Computer-Assisted - methods; Linear Models; Magnetic Resonance Imaging - methods; mass-univariate GLM; Mathematical models; Models, Neurological; Models, Theoretical; Neuroimaging; nuisance variables; mass-univariate GLM; Bayesian model averaging; nuisance variables; correlated regressors; cross-validation; fMRI-based neuroimaging

In functional magnetic resonance imaging (fMRI), model quality of general linear models (GLMs) for first-level analysis is rarely assessed. In recent work (Soch et al., 2016: “How to avoid mismodelling in GLM-based fMRI data analysis: cross-validated Bayesian model selection”, NeuroImage, vol. 141,...