Dear SPMler,
I am new to SPM and have to excuse me for a perhaps very basic question: I would like to compute contrasts for an 2*3 ANOVA.
I have a design were participants read words given by a person or computer (source: S1, S2), which had a negative, neutral or positive quality (emotion: E1, E2, E3).
I have calculated a flexible factorial ANOVA. For the flexible factorial ANOVA I would like to calculate a main effect for source, a main effect for emotion and an interaction effect. I have listed it in the following order:
S1; S2; E1; E2; E3; S1*E1; S1*E2; S1*E3; S2*E1; S2*E2; S2*E3;
and the contrast for the interaction are the following:
[0 0 0 0 0 1 -1 0 -1 1 0
0 0 0 0 0 0 1 -1 0 -1 1]
so as far as I understand, this should lead to S1*E1+S2*E2 = S1*E2+S2*E1 = S1*E2+S2*E3 = S1*E3+S2*E2, and if any of those means do differ, there should be an interaction. Does this sound reasonable? If not, what would you suggest me to use in the contrast vector?
I have read the Henson&Penny paper about ANOVAs, but sadly, I am still unsure about the 2*3 ANOVA.
Thank you for your help.
Best regards
Sebastian Schindler
|