Dear FSL brainiacs,

Nan Wise here with what I hope is a quick question.  I am trying to determine whether there is a significant difference between two conditions-- The n is small  --6 participants in one condition--3 in the other (not within S design).  

I set up a unpaired t-test --and got very different results with FLAME1 versus FLAME 1+2.  What is the best statistic to use when you have a small n?  I haven't tried FIXED EFFECTS,  or MIXED EFFECTS OLS yet.

What is the most reliable statistic in this case? I  would like to have a good rationale for the choice.  

Thanks so much,

Nan Wise
PhD candidate--Cognitive Neuroscience
Rutgers-Newark