Dear FreeSurfer Experts,
In the example here: http://surfer.nmr.mgh.harvard.edu/fswiki/Fsgdf1G2V, it describes the testing of the main effects of two continuous variables.
In order to test the interaction effect, I think we can form an interaction term like age x weight as the third covariate, that is,
Regressor1: All ones. Codes intercept/mean for Main Regressor2: age for each subject. Codes age slope for Main Regressor3: weight for each subject. Codes weight slope for Main Regressor4: age x weight for each subject. Codes age x weight interaction effect
and then specify a contrast [0 0 0 1]?
Is that the way to go?
Best, Daniel
-- Daniel (Yung-Jui) Yang, Ph.D. Postdoctoral Researcher Yale Child Study Center New Haven, CT Tel: (203) 737-5454 E-mail: yung-jui.yang@yale.edu
Yes. doug
On 2/21/14 6:15 AM, Yang, Daniel wrote:
Dear FreeSurfer Experts,
In the example here: http://surfer.nmr.mgh.harvard.edu/fswiki/Fsgdf1G2V, it describes the testing of the main effects of two continuous variables.
In order to test the interaction effect, I think we can form an interaction term like age x weight as the third covariate, that is,
Regressor1: All ones. Codes intercept/mean for Main Regressor2: age for each subject. Codes age slope for Main Regressor3: weight for each subject. Codes weight slope for Main Regressor4: age x weight for each subject. Codes age x weight interaction effect
and then specify a contrast [0 0 0 1]?
Is that the way to go?
Best, Daniel
-- Daniel (Yung-Jui) Yang, Ph.D. Postdoctoral Researcher Yale Child Study Center New Haven, CT Tel: (203) 737-5454 E-mail: _yung-jui.yang@yale.edu_
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
freesurfer@nmr.mgh.harvard.edu
-
Douglas Greve -
Yang, Daniel