Hi Johny,
hopefully Tom Nichols will give you a more solid answer than mine for this reviewer in the next couple of days, but in the mean time, you can have a look at this email I've sent some time ago, indicating what the reviewer has in mind:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?A2=ind1004&L=FSL&P=R14807&I=-3&d=No+Match%3BMatch%3BMatches
Good luck,
Gwenaelle
> De: SUBSCRIBE FSL Anonymous <[log in to unmask]>
> Objet: [FSL] TBSS Randomise t-test
> À: [log in to unmask]
> Date: Mardi 22 mars 2011, 0h09
> Dear FSL experts,
>
> Following the instruction TBSS analysis on DTI dataset, we
> applied randomise on group comparison and find difference
> between groups (there are total 3 groups: 2 different
> patient groups and one control group). However, the reviewer
> asked the following question:
> "There is insufficient description of how the between-group
> comparisons were performed, and that should be rectified.
> Furthermore, in this three-group study, it appears that the
> between-group analysis consisted of multiple pairwise
> t-tests (or the equivalent) rather than an omnibus ANOVA (or
> its equivalent). Please present an analysis that includes
> all three groups in one statistical model.".
> Could you please help us answer those questions,
> specifically regarding the t-test from the permutation
> inference?
> Many thanks in advance.
>
> Johny
--------------------------------------------------------------------
Gwenaëlle Douaud, PhD
FMRIB Centre, University of Oxford
John Radcliffe Hospital, Headington OX3 9DU Oxford UK
Tel: +44 (0) 1865 222 523 Fax: +44 (0) 1865 222 717
www.fmrib.ox.ac.uk/~douaud
--------------------------------------------------------------------
|