Dear FS list,
I have a data set with 3 groups (2 treatments, 1 control),
each with equally-spaced time-points (pre and post structural
scan). I've done the 3 longitudinal pre-processing steps, and
stage#1 of the two-stage model, and I would prefer to run
stage#2 (cross-sectional analysis of the difference) with QDEC
as opposed to with mri_glmfit.
I know that QDEC is meant for 2 groups, but I see that designs
with 4 or 6 groups can be analysed with QDEC (as per
this FSGD examples page) whereas designs
with 3 groups cannot be. It seems to me that an even number of
groups is QDEC-able while an odd number isn't, but is there
any workaround so that I can still use QDEC? Perhaps if I only
do pairwise comparisons one at a time, i.e. treatment1 vs
control and treatment2 vs control?
Many thanks!