Hello,
I have a fairly simple question regarding a mixed design. I am aware of the issues surrounding the error terms for mixed designs, but I have a 2 (condition) x 2(group) design and I am wondering how best to approach it. I have been given mixed information regarding what is valid and I am just wondering if I could get a little guidance.
I have entered contrasts at the first level to look at my experimental condition minus my control condition (i.e., C1>C2; 1 -1) and I am now wanting to look at that between the groups. Is it okay to use these contrasts in a t-test at the second level to look at the differences between the groups (i.e., G1>G2; 1 -1)? Or do I need to use first level contrasts that are not weighted (i.e., first level contrast 1 0)? Is this the best way to go around it or is it better to set up a factorial at the second level?
Thanks for all your help
Meg
|