Hi Ulas,

Almost! You also need to enter an intercept (i.e., an EV that is a column full of ones), or use the option -D in randomise, so that both data and design are mean-centered.

You may also want to consider the opposite contrasts, i.e., add 3 more that are the same as you have, but with -1 instead of 1.

All the best,

Anderson

On Mon, 22 Oct 2018 at 08:41, Ulas Ay <[log in to unmask]> wrote:

I am sorry for not adding attachments. I have 30 participants (one group) and each participant has a functional connectivity matrix of size 148x148. I wanna see the gender, age and education effect on functional connectivity.

Is it correct the desing matrix for randomise?

Ulas

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

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