Missingness in fMRI Studies: Multiple Imputation

Limited imaging coverage of the brain and susceptibility artifact contributes to missing data in functional imaging studies.  Multiple imputation is one solution for dealing with missing data.  We demonstrate in a recent Neuroimage manuscript the considerable benefit of using multiple imputation in functional imaging studies. There was a 35% increase in the number of voxels that were analyzed in a group study when multiple imputation was used to “fill in” missing data.  This approach will help to reduce the number of false negative results, increase power, and increase the validity of whole brain studies, particularly those involving large open access databases and ultra high-field imaging.