Hi,
This is generally correct but you should demean your covariate scores before putting them into the design matrix.
See: http://fsl.fmrib.ox.ac.uk/fsl/fslwiki/GLM#Two-Group_Difference_Adjusted_for_Covariate
All the best,
Mark
On 8 Jan 2014, at 13:07, Hamzah Baagil <[log in to unmask]> wrote:
> Dear FSLexperts,
>
> I would like to compare patients vs controls in TBSS analysis including the covariate UPDRS score. However I am not sure if my design contrast and matrix is correct, which looks like this
>
> /ContrastName1 Controls > Patients
> /ContrastName2 Patients > Controls
> /ContrastName3 UPDRS
> /NumWaves 3
> /NumContrasts 3
> /PPheights 1.092957e+00 1.092957e+00 4.000000e+01
> /RequiredEffect 2.849 2.849 3.235
>
> /Matrix
> 1.000000e+00 -1.000000e+00 0.000000e+00
> -1.000000e+00 1.000000e+00 0.000000e+00
> 0.000000e+00 0.000000e+00 1.000000e+00
> hbaagil@u1:/daten/kfo/KFO_group/Hamzah/TBSS_projects/Projekt_arbeit/fsl-5.0.4/tbss2_reg-T/patients_vs_subjects_covariate_UPDRS_P_5000/stats$ more design.mat
> /NumWaves 3
> /NumPoints 46
> /PPheights 1.000000e+00 1.000000e+00 5.100000e+01
>
> /Matrix
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 1.000000e+00 0.000000e+00 0.000000e+00
> 0.000000e+00 1.000000e+00 3.100000e+01
> 0.000000e+00 1.000000e+00 4.500000e+01
> 0.000000e+00 1.000000e+00 1.800000e+01
> 0.000000e+00 1.000000e+00 2.400000e+01
> 0.000000e+00 1.000000e+00 4.500000e+01
> 0.000000e+00 1.000000e+00 1.100000e+01
> 0.000000e+00 1.000000e+00 1.900000e+01
> 0.000000e+00 1.000000e+00 1.700000e+01
> 0.000000e+00 1.000000e+00 1.500000e+01
> 0.000000e+00 1.000000e+00 5.100000e+01
> 0.000000e+00 1.000000e+00 2.200000e+01
> 0.000000e+00 1.000000e+00 2.600000e+01
> 0.000000e+00 1.000000e+00 2.500000e+01
> 0.000000e+00 1.000000e+00 2.500000e+01
> 0.000000e+00 1.000000e+00 2.500000e+01
> 0.000000e+00 1.000000e+00 2.800000e+01
> 0.000000e+00 1.000000e+00 4.000000e+01
> 0.000000e+00 1.000000e+00 4.500000e+01
> 0.000000e+00 1.000000e+00 2.000000e+01
> 0.000000e+00 1.000000e+00 3.700000e+01
> 0.000000e+00 1.000000e+00 2.900000e+01
> 0.000000e+00 1.000000e+00 3.600000e+01
> 0.000000e+00 1.000000e+00 1.900000e+01
>
> I would appreciate any help.
>
> Thank you,
> Hamzah
|