try looking at the FSGD examples for a case that you can generalize

https://surfer.nmr.mgh.harvard.edu/fswiki/FsgdExamples

On 08/29/2017 08:59 PM, Ines Mürner-Lavanchy wrote:

Dear FS experts,

I would like to test if the correlations between thickness/area and cognition differ between two groups, while age, socioeconomic status (continuous) and gender (dichotomous) should be nuisance variables.

To look at the effect of cognition in one group only, I made a model with 8 regressors:

• sex male
• sex female
• age male
• age female
• cognition male
• cognition female
• ses male
• ses female

With the contrast 0 0 0 0 0.5 0.5 0 0: how does cognition correlate with Cth/CSA, controlled for age, sex, and ses.

Now how do I model this, if I have *two* groups and want to look at the interaction of group*cognition? I have trouble setting up the fsgd and design matrix.

Any help is appreciated,

Thanks in advance,

Ines

---

Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer