I am trying to perform an anova like analysis using 3ddeconvolve using the -glt option.
Data was collected in 10 session, each condition applied seperately per conditions. A block design with 30 s rest alternating with 30 s activity was used. I have 2 factors. Factor A has two levels and factor B has five. They are arranged (using 3dTcat) in the following order:
A1B1 A1B2 A1B3 A1B4 A1B5 A2B1 A2B2 A2B3 A2B4 A2B5
I think I understand how to look for main effects. A main effect of A would test whether the row means were equal which I think would look like this in a -glt file
1 1 1 1 1 -1 -1 -1 -1 -1
A main effect of B would show if any columns were not equal and I think would require a combination of all condition pairs:
1 -1 0 0 0 1 -1 0 0 0
1 0 -1 0 0 1 0 -1 0 0
1 0 0 -1 0 1 0 0 -1 0
1 0 0 0 -1 1 0 0 0 -1
0 1 -1 0 0 0 1 -1 0 0
0 1 0 -1 0 0 1 0 -1 0
0 1 0 0 -1 0 1 0 0 -1
0 0 1 -1 0 0 0 1 -1 0
0 0 1 0 -1 0 0 1 0 -1
0 0 0 1 -1 0 0 0 1 -1
but I am not sure on how test for the presense of an interaction.
Any help would be greatly appreciated.
KJ
