 |
 |
Dear fsl community, I am getting mixed opinions about the implementation of my group analysis, hence I decided to post my question here. I just want to make sure that my FEAT setup is correct as I am switching to fsl from other softwares. I have two groups of subjects (healthies and patients) - my fixed factor. All of them performed two conditions (experimental and control) - my random factor. I followed this http://fsl.fmrib.ox.ac.uk/fsl/fslwiki/GLM#ANOVA:_2-factors_2-levels_.282-way_between-subjects_ANOVA.29 to set up my higher-level analysis. My questions are: 1. Is that the correct set up to use in FEAT in my case? 2. Because of the mixed design we need to do the extra step outlined in the user guide to find out the random effects. However, should that random effect be derived from running it through Fixed Effects or FLAME in the Stats tab. That is, do I use FLAME for this group analysis or Fixed Effects in the stats tab? 3. Do I need to model subject variance? This isn't in the online example for mixed between-subject designs, but want to make sure... Thank you in advance for your help.