R/lmerCluster.R
lmerCluster.RdThis function is able to run a LME using the lmer() function. All clusters or region of interest must be labeled with integers in the mask passed as an argument. The function relies on lmerTest to create p-values using the Satterthwaite Approximation.
lmerCluster(image, mask, fourdOut = NULL, formula, subjData,
mc.preschedule = TRUE, ncores = 1, ...)Input image of type 'nifti' or vector of path(s) to images. If multiple paths, the script will call mergeNifti() and merge across time.
Input mask of type 'nifti' or path to mask. All clusters must be labeled with integers in the mask passed as an argument
To be passed to mergeNifti, This is the path and file name without the suffix to save the fourd file. Default (NULL) means script won't write out 4D image.
Must be a formula passed to lmer()
Dataframe containing all the covariates used for the analysis
Argument to be passed to mclapply, whether or not to preschedule the jobs. More info in parallel::mclapply
Number of cores to use
Additional arguments passed to lmer()
Returns list of models fitted to the mean voxel intensity a region or interest.
image <- oro.nifti::nifti(img = array(1:1600, dim =c(4,4,4,25)))
mask <- oro.nifti::nifti(img = array(c(rep(0,14),1,2), dim = c(4,4,4,1)))
set.seed(1)
covs <- data.frame(x = runif(25), id = rep(1:5,5))
fm1 <- "~ x + (1|id)"
models <- lmerCluster(image, mask, formula = fm1, subjData = covs, ncores = 1, REML=TRUE)
#> [1] "Created meanCluster Matrix"
#> [1] "Created formula list"
#> [1] "Running test model"
#> boundary (singular) fit: see help('isSingular')
#> [1] "Running parallel models"
#> boundary (singular) fit: see help('isSingular')
#> boundary (singular) fit: see help('isSingular')
#> elapsed
#> 0.082
#> [1] "Parallel Models Ran"