Hi - if the tests are fully independent then the most safe
(conservative) thing to do is just to test for corrected p<(0.05/
N_contrasts) instead of p<0.05.
Though that's more careful than many people are!
Cheers, Steve.
On 6 Jul 2007, at 18:02, Ping-Hong Yeh wrote:
> Hi Steve,
>
> If I need to correct the stats for multiple contrasts using
> Bonferroni, how
> would that be pursued after correction of voxle-wise analysis?
>
> Thanks a lot.
> Ping
------------------------------------------------------------------------
---
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
------------------------------------------------------------------------
---
|