20 Nov
2009
20 Nov
'09
12:52 p.m.
Hi Jon,
what statistical tests are you running? That defines what the bonferroni correction will be. For example, if you are testing for thickness differences in each parcellation unit, then you need to correct for the # of parcels.
cheers, Bruce
On Fri, 20 Nov 2009, Jonathan DuBois wrote:
When correcting for multiple comparisons with Bonferroni for FS parcilation statistics, is it necessary to adjust for all parcellations (35) or just the variables (in our case mean thickness and surface area)? Assuming that no prior hypothesis is used to constrain the number of parcellations.
Thanks for you input!
Jon