You shouldn't be using covariates in a repeated-measures design
implemented using a GLM.
If you want to know if the covariate correlates with the difference in
your measures, form a difference image for each subject and then use a
one- or two-sample t-test with a covariate.
Also, your Gp1_Cond1 (along with any other contrast of a single
condition) is invalid because of SPM uses the wrong error term. GLM
Flex or a one-sample t-test would be the correct test to use.
Best Regards, Donald McLaren
=================
D.G. McLaren, Ph.D.
Research Fellow, Department of Neurology, Massachusetts General Hospital and
Harvard Medical School
Postdoctoral Research Fellow, GRECC, Bedford VA
Website: http://www.martinos.org/~mclaren
Office: (773) 406-2464
=====================
This e-mail contains CONFIDENTIAL INFORMATION which may contain PROTECTED
HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED and which is
intended only for the use of the individual or entity named above. If the
reader of the e-mail is not the intended recipient or the employee or agent
responsible for delivering it to the intended recipient, you are hereby
notified that you are in possession of confidential and privileged
information. Any unauthorized use, disclosure, copying or the taking of any
action in reliance on the contents of this information is strictly
prohibited and may be unlawful. If you have received this e-mail
unintentionally, please immediately notify the sender via telephone at (773)
406-2464 or email.
On Sat, Jan 26, 2013 at 5:27 PM, Delphine Roussillon
<[log in to unmask]> wrote:
> I did a SPM model with flexible factorial design in which I have two groups
> and two conditions.
> The design matrix looks then like that :
>
> Gp1 Gp2 Cond1 Cond2 Gp1xCond1
> G1xCond2 Gp2xCond1 Gp2xCond2 SubjectsGp1(13 columns) SubjectsGp2(14
> columns)
>
> I did my contrasts and all is ok, for example :
> Gp1_Cond1 : 1 0 1 0 1
> 0 0 0 ones(1,13)./13
> zeros(1,14)
> Gp1_Cond1>Cond2 0 0 1 -1 1
> -1 0 0 zeros(1,13)
> zeros(1,14)
>
> Then I tried to add a covariate in my model so I have (no interaction
> between covariate and factor) :
>
> Gp1 Gp2 Cond1 Cond2 Gp1xCond1
> G1xCond2 Gp2xCond1 Gp2xCond2 covariate SubjectsGp1(13 columns)
> SubjectsGp2(14 columns)
>
> And I don't understant why when I add this covariate (IQ) this contrats
> works :
>
> Gp1_Cond1>Cond2 0 0 1 -1 1
> -1 0 0 0
> zeros(1,13) zeros(1,14)
>
> But not this one anymore although I need to look just at my conditions (and
> not only the interaction Cond1-Cond2 or Cond2-Cond1) :
>
> Gp1_Cond1 : 1 0 1 0 1
> 0 0 0 0
> ones(1,13)./13 zeros(1,14) ("invalid contrast")
>
>
> Thank you very much for your help
> Delphine
