I have two groups (factor A). I have 12 conditions (factor B). I have an unbalanced number of subjects in each group (factor C, 12 and 9). When I run GroupAna type 3 with unbalanced design I get some very inflated t and F values (F > 7000, t > 60 for all contrasts and factor main effects). I don't believe I am doing anything wrong, since I ran it before with a balanced design (by knocking out some subjects) and it worked great. I have attached my inputs to the program, and recieve no errors while it is running. It there a way to diagnose this problem? While I wait for a response, I will try to get R and 3dLME up and running in the hopes that it will give more tractable statistical results. Thankyou for all of your help!
-Daniel