Hi,
I have a pilot study in which the number of subjects in each group is quite small. At the moment for each group I am running a fixed effect analysis and then doing a conjuction (each subject is modeled with their own stimulus and baseline regressors) by selecting all contrast (ie 1 -1 0 0 0 0 0 0 0 and 0 0 1 -1 0 0 0 0 etc). (as per http://www.mailbase.ac.uk/lists/spm/2000-06/0061.html)
However, I now what to examine the difference in the activation between groups. Normally with larger, equally balanced groups I could do a 2-sample t-test, but the group populations are low (5 and 4 respectively).
Help?
Thanks,
Robert Welsh
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|