[UNDER DEVELOPMENT] neuroCombat harmonization using parameters estimated from a training dataset. Estimated parameters are applied to a new dataset, assuming scanners/batches in the new dataset were also present in the training dataset.

neuroCombatFromTraining(dat, batch, estimates, mod = NULL, verbose = TRUE)



Numeric matrix with imaging features as rows, and scans/images as columns.


Numeric or character vector specifying the batch/scanner variable needed for harmonization. Length must be equal to the number of columns in dat.


Prior neuroCombat estimates to be applied onto the new dataset. Usually obtained from the output of neuroCombat run on a training dataset.


Optional model matrix for outcome of interest and other covariates besides batch/scanner.


Should progress messages be printed? TRUE by default.


A named list of length 2. The first element (dat.combat) contains the harmonized data. The second element (estimates) contains estimates and other parameters used during harmonization.