I just want to check. I have a model where a want to check the correlation between a continous parameter A and FA correcting for sex and age. Only one group.
The design file is then:
group gender age A
And group as all ones and then the cont. values for each patient (not demeaned as randomize does that for you).
I am intereseted in the effect of A accountong for the effect of sex and age, giving a contrast file as
0 0 0 -1 (neg correlation assumed)
Is this correct?
Just to check, if I want the separate effect of sex and age corrected for the others, would that be:
0 0 0 -1 # A (corresponding to stat-files number 1)
0 1 0 0 # sex (coresp to no 2)
0 0 -1 0 # age (corresp to 3)
Is this the way to interpret it, i.e. the stat-file numbering refers to the lines in the contrast file?
best nick