Preliminary Statistics
An initial paired or unpaired t-test will be computed per data-point to retrieve a preliminary statistical comparison between groups / conditions. Results can be used to define time-windows and /or frequency-windows of interest that will be passed on to permutation testing.
Clustering in time and if applicable space and frequency is based on the preliminary t-test. Depending on the cluster-alpha setting, adjacent data points will be subsumed to form a cluster. The significance of these data clusters will be probed during permutation testing.
Preliminary Statistics ERP Data
After running the preliminary t-test, the test results can be reviewed in order to define a region of interest, set statistical parameters for permutation testing and average over time and / or frequency and channels.