Hi all,
I'm running an anova test with 4 factors, each at 2 levels, repeated measures, on 6 subjects. First, I would like to know if my setup is correct (I modeled the design and contrasts similar to the Anova: 3 factors 2 levels example on the feat higher level analysis manual) with the following EVs:
EV1 EV2 EV3 EV4 EV5 EV6 EV7 EV8 EV9 EV10 EV11 EV12 EV13 EV14 EV15 EV16-21
a b c d ab ac ad bc bd cd abc abd acd bcd abcd s1-s6
My other question is regarding the correction for random effects/mixed effects factors. On the bottom of the Feat higher level analysis manual, there are examples of how to correct for random effects and mixed effects factors using fslmaths and so forth. Since I have a small sample of subjects, would it be more appropriate to regard the factors as fixed? If they are fixed factors, do I still run the analysis with "Mixed Effects Flame 1" under the stats tab in FEAT, or do I run it with the "Fixed Effects" option?
Thanks,
Amy
|