With one group of subject and one covariate, your model is something like this
y = a + b*x + e
> When examining the results of the 3dttest++ in afni, do results produced by entering
> behavior t-stat as the threshold represent behavior varying with connectivity or mean
> connectivity for all participants covarying behavior?
There should have four values (sub-bricks) in the output: the first two correspond to the intercept or constant 'a' (mean connectivity in your case if you center the covariate properly) in the above model, and the next two are for the covariate effect 'b' (behavioral effect).
> I’m interested in the relationship between connectivity and behavior.
b and its t-statistic are what you're looking for.
Gang
Edited 2 time(s). Last edit at 05/24/2013 12:23PM by Gang.