Greetings Gang:

Thank you for your response. It seems clear then that we will need to run the ANOVA model separately for each contrast.

What is not clear to us is:

1. For the 2nd ANOVA model (which inlcudes 4 levels of factor b), do we need the "a" factor (which specifies controls and patients) at all or is it redundant with factor b?

2. Why does "-dset 1 1 2" intrinsically not exist? To clarify, for the first ANOVA model, factor "a" refers to the "group" which is the between-subjects factor, while factor "b" refers to "run" which is the within-subjects factor . Thus, 1 1 2 means a control subject, run1, subject#2. This seems to exist to us (poor subject if she does not exist!). Are we being obtuse?

3. We want to know if the interaction extracted in the first ANOVA model by "-fab GrpxRun" and in the second ANOVA model coded by "Interaction Factor1 by Factor2: 1 -1 -1 1 " should yield the same or different brain maps? Is this 2nd model coding correct for determining the presence of an interaction of Group x Run?

4. Under factor c (random factor for subjects in the study) we were under the impression that if there are 12 subjects per group (24 subject total) we should code this as 1 through 12 once for the controls and 1 through 12 for the patients for each level of factor b in the first model.

For the second model in which factor b has 4 levels, controls go with level 1 and 2, patients go with levels 3 and 4. We then coded controls 1-12 once for level 1 and again for level 2; patients 1-12 once with level 3 and again for level 4.

Are we doing this correctly? Any and all feedback will be greatly appreciated.

We will try to run both ANOVA models and report back.

wiveka & philippe