Print

Print
Hi Jean,

Assuming that you're using FEAT (Higher-level analysis), in the 'stats' table you can select the option 'Full model setup' and add the covariates (sex, age, etc.) as EVs. Then your design matrix will look like this (if you add sex as one EV where, e.g., male = 1 and female = -1):

high low NC age sex
1      0    0    20    1
1      0    0    22    1
...
0      1    0    21   -1
0      1    0    20   -1
...
0      0    1    23   -1
0      0    1    20    1
 
Is this what you're looking for?

Best,

Bianca


Em seg, 30 de set de 2019 às 11:10, Jean Kim <[log in to unmask]> escreveu:
Dear FSL experts,

hello, I have a quick question about how to run ANCOVA on GLM GUI.

Briefly explain about my study, I have three groups (high disease, low disease, normal control).
I already run the 3 t-test (high vs low; low vs NC; high vs NC), and it showed some significance.

I just want to run ANCOVA for the three groups! but I cannot find any manual on GLM..
- covariates would be age sex edu ,etc.


Please help me out how to establish GLM!!
Thank you in advance.

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

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

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