Hi Ye, don't select the same factor as nuisance and covariate. It will result in an error for sure. The difference between a covariate and a "nuisance" factor is purely conceptual. By calling something a nuisance you tell QDEC not to create a contrast related to it. doug
On 08/13/2013 02:09 AM, ye tian wrote:
Dear Freesurfers, I have a question concerning the "nuisance factors" in the qdec dialogue. Suppose I have two independent variables x1 (discrete) and x2 (continuous), and only one observable y. I choose "Discrete (Fixed factor) = x1", "Continuous (covariate) = x2". If I further chose "Nuisance factor = x2", does that imply that
- my contrast matrix is (0 1)
- null hypothesis: Y is independent of x2
Thank you very much! Sincerely, Ye
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer