Hi Tae-Ho,

The GLM (and also nets_glm) doesn't know the difference between covariates and other EVs, so this is absolutely fine. Note that you are running multiple regression, so the presence of EV1, EV2, ... will affect your result for Age even if there is a zero in the design matrix for these EVs.

Best wishes,

Janine

On Mon, Aug 5, 2019 at 6:24 PM THLee <[log in to unmask]> wrote:

Dear FSL and users,

I am planning to run glm with fslnets. I have created my design contrast and matrix. Actually, I would like to test whether a certain variable (e.g., age) influences connectivity status or not. So I am planning to run nets_glm in following ways

1) put a demeaned covariate in the last column of the regular design matrix (e.g., [EV1, EV2, ... EVn, Age])
2) create contrast matrix related this variable (e.g., age-positive [ 0, 0, ... 0, 1] or age-negative [0, 0, ... 0, -1]).
3) run 'nets_glm' with these design matrix and contrast file.

Please let me know if this is not right or there is no way running 'nets_glm' with covariates.

Thank you for your feedback.

Best,

Tae-Ho

########################################################################

To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1

--

Janine Bijsterbosch
Assistant Professor of Radiology

Washington University in St Louis

Radiology East Building (office #3348)
4525 Scott Avenue, Campus Box 8225 

My Pronouns: she/her or they
[log in to unmask]  
Website: https://sites.wustl.edu/personomics/ 

---

To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1