Hi Matthew -
Looks good to me. Hopefully the true nuisance variables aren't so
counfounding as your examples!
Eugene
--
Centre for Functional MRI of the Brain (FMRIB) | University of Oxford
John Radcliffe Hospital | Headington
OX3 9DU | Oxford | UK
Ph: +44 (0) 1865 222 523 | Mob: +44 (0) 7946 362 059 | Fax: +44 (0) 1865 222 717
--
On 27 May 2010 17:30, Matthew Schroeder <[log in to unmask]> wrote:
> Hi there,
> I just want to make sure that I have the appropriate design for an ANCOVA I am trying to set up for a VBM analysis. I have 4 groups (control, disease 1, disease 2, disease 3) and want to include demeaned age (EV5) and demeaned interhemispheric volume (EV6) as nuisance variables. I want to perform F-tests to see if there are any differences between the groups. For ease of displaying, I've included 2 subjects from each group and hypothetical values for age and volume.
>
> Does the following look right for what I want to accomplish?
>
> DESIGN
> Group EV1 EV2 EV3 EV4 EV5 EV6
> 1 1 1 0 0 3 -200000
> 1 1 1 0 0 3 -150000
> 1 1 0 1 0 5 -100000
> 1 1 0 1 0 2 -50000
> 1 1 0 0 1 -1 50000
> 1 1 0 0 1 -4 100000
> 1 1 0 0 0 -6 150000
> 1 1 0 0 0 -2 200000
>
> CONTRASTS
> Title EV1 EV2 EV3 EV4 EV5 EV6 F1
> X A-D 0 1 0 0 0 0 X
> X B-D 0 0 1 0 0 0 X
> X C-D 0 0 0 1 0 0 X
>
>
|