for me this looks fine. If you want to test differences between your two
groups, you will have to weight the subject factors as you would do for
each group main effect. For 2 groups with size N1 and N2 this would look
1/N1*ones(1,N1) -1/N2*ones(1,N2) 1 0 -1 0
Note that even though
zeros(1,N1+N2) 1 0 -1 0
would sum up to zero, it is still invalid, because the condition columns
are not independent of the subject columns.
On Tue, 11 Sep 2007, Nicholas O. Rule wrote:
> Hi Volkmar,
> Thanks for your help. I'm not sure if by "batch" you mean a script that
> automated the model and contrasts. I entered all of the arguments manually...
> I'm enclosing my 2nd-level specification file, which I think may provide the
> information you're referring to?
> Thanks again,
> Quoting Volkmar Glauche <[log in to unmask]>:
>> Dear Nicholas,
>> to understand what is going on, it would help to have a look at the SPM
>> batch you used to specify and estimate your model and contrasts - please
>> send one example to me (no images, no SPM.mat, just your saved batch
>> On Mon, 10 Sep 2007, Nicholas Rule wrote:
>> > Hi everyone,
>> > I have been trying to test a mixed-model factorial design in SPM5 with
>> > no success. A few others from the list have recently posted similar
>> > questions, we have been in touch, but none of us has found a solution.
>> > What we do know is that we need to model subjects in a flexible
>> > factorial. We are able to test the within-subjects factor but the
>> > contrast manager won't let us test the between-subjects factor (we are
>> > told that the contrasts are invalid, even though they sum to 0).
>> > Does anyone know why this might be happening or what we can do to solve
>> > the problem? I've honestly tried everything I can think of.
>> > Thanks a lot,
>> > Nick Rule
>> Volkmar Glauche
>> Department of Neurology [log in to unmask]
>> Universitaetsklinikum Freiburg Phone 49(0)761-270-5331
>> Breisacher Str. 64 Fax 49(0)761-270-5416
>> 79106 Freiburg http://fbi.uniklinik-freiburg.de/
Department of Neurology [log in to unmask]
Universitaetsklinikum Freiburg Phone 49(0)761-270-5331
Breisacher Str. 64 Fax 49(0)761-270-5416
79106 Freiburg http://fbi.uniklinik-freiburg.de/