Dear all,
I have a question about multiple comparison correction with randomise results. I collected FWE-corrected p values with threshold-free cluster enhancement from a permutation test between structural maps and language scores for one group of individuals.
However, I am testing the association between the same group of maps and 6 different behavioral tests independently. Therefore, I am applying a Bonferroni correction on the maps to account for the 6 permutation tests. As randomise output is 1-p, I transformed the maps with -mul -6 -add 6 (comes from y=1-p --> 6y = 6 – 6p --> 6p = 6-6y).
Is it a correct way to do these multiple comparison corrections or is there a better way to modify these maps and obtain the corrected p value for multiple testing? I know that it is better to change the alpha criterion rather than the p value but I would like to change the maps to get the direct visualization of the significant values.
Many thanks in advance for your help.
Best regards,
Anne Billot
########################################################################
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1
|