 |
 |
Hi Paul, Sorry for introducing myself in the talk. But could you tell me how did you conducted FDR in the tfce not corrected stats? Thank you, Rosalia. El 01/10/2014 22:32, "Paul Beach" <[log in to unmask]> escribió: > > Anderson, > > Thank you so much for the quick reply. I'd like to ask a follow-up, please. > > So after I run FDR on the uncorrected TFCE p-value files, I do not have to perform follow-up corrections (like with FWE correction) based on how many networks I examine, correct? > > On Wed, Oct 1, 2014 at 4:17 PM, Anderson M. Winkler < [log in to unmask]> wrote: >> >> Hi Paul, >> It's fine to use FDR on the otherwise uncorrected TFCE p-values -- but not on the corrected TFCE p-values. >> All the best, >> Anderson >> >> >> On 1 October 2014 21:02, Paul Beach <[log in to unmask]> wrote: >>> >>> FSLers, >>> >>> I'm still a little confused after reading through the archives on this issue and wanted quick clarification, if possible. >>> >>> Am I correct in surmising that it is inappropriate to apply FDR correction to TFCE results (i.e. one must use results from the voxel-based option in randomise)?. >>> >>> >>> Thanks >>> -- >>> Paul Beach >>> DO/PhD candidate - Year VI >>> Michigan State University >>> - College of Osteopathic Medicine >>> - Neuroscience Program >>> - MSU Cognitive and Geriatric Neurology Team (CoGeNT) >> >> > > > > -- > Paul Beach > DO/PhD candidate - Year VI > Michigan State University > - College of Osteopathic Medicine > - Neuroscience Program > - MSU Cognitive and Geriatric Neurology Team (CoGeNT) n