Hi,
We've noticed that FDR correction produces different p-values for the left and right hemispheres. We found that this issue was observed previously and an email was sent to the mailing list (see below), however, no answer was received. We wondered if anybody has noticed this problem before and if there are any suggestions on how best to deal with it.
Thanks Manja
Hi, FDR correction for multiple comparisons gives you different p-values for the left and right hemispheres. It seems really weird to report in a paper: a) that you've corrected for the right and left hemispheres separately and b) that the p-value that gave rise to a corrected probability of .05 was different for each. How do people deal with this issue? Take the most stringent p-value and use it for both hemispheres? Just report that FDR adjusted the p- value to .05?
Also, correcting for right and left hemispheres separately assumes that they are independent observations. Unless you're studying callosotomy patients (and maybe even if you are) this doesn't seem justified. Are we supposed to be adjusting p-values accordingly?
Thanks, Dara