Pravesh Parekh, Chun Chieh Fan, Oleksandr Frei, Clare E Palmer, Diana M Smith, Carolina Makowski, John R Iversen, Diliana Pecheva, Dominic Holland, Robert Loughnan, Pierre Nedelec, Wesley K Thompson, Donald J Hagler, Ole A Andreassen, Terry L Jernigan, Thomas E Nichols, Anders M Dale
The linear mixed-effects model (LME) is a versatile approach to account for dependence among observations. Many large-scale neuroimaging datasets with complex designs have increased the need for LME; however LME has seldom been used in whole-brain imaging analyses due to its heavy computational requirements. In this paper, we introduce a fast and efficient mixed-effects algorithm (FEMA) that makes whole-brain vertex-wise, voxel-wise, and connectome-wide LME analyses in large samples possible. We validate FEMA with extensive simulations, showing that the estimates of the fixed effects are equivalent to standard maximum likelihood estimates but obtained with orders of magnitude improvement in computational speed...
February 1, 2024: Human Brain Mapping