Hello @rsmith and all,
I have a very simple question:
When specifying multiple rows in the contrast matrix, does connectomestats already perform Bonferroni correction for multiple-comparisons by multiplying the resulting p-values by the number of rows?
This is especially relevant to the common contrast matrix used for simulating a two-tailed t-test:
0 1 -1
0 -1 1
Can I just use the p-values spat out by connectomestats, or need to multiply them by 2 myself?
Not directly related to MRtrix, but do you happen to know how it works in FSL’s randomise?