Hi all,
I also have a question regarding longitudinal fMRI modelling.
Background: I have 3 groups, 2 time points, and only 1 contrast. I use a flexible factorial design.
I am really interested only in the group-by-time interaction.
Initially, I wanted to model all effects: subject, group, time, and group-by-time interaction.
I have read few posts on the topic, and it seems clear that looking at the effect of group when using the flexible factorial design in SPM is not recommended.
But should I still model group in my design (without inferring anything about it), or just keep time (contrast [2]), subject (contrast [3]) and interaction (contrast [1 2])?
What about the effect of time? Is it valid to look at the effect of time within this model? Similarly, should I keep it in the model if I am only interested in the effect of the interaction term?
Thanks for your help.
Yann
|