Dear Markus
From what I can see, the setup is basically correct: You have a 2x4 design and hence 8 cells, which you are to fill with the respective baseline contrasts.
The error you get indicates that the number pf points in your data matrix is unequal to the length of the indicator vectors. As for as I know, SPM allows for unbalanced designs, that is for a different number of scans per cell, so that should not be the problem.
Just by chance, you did not miss a cell? Maybe it is worth checking the setup again, otherwise I would defer this question to people more experinced in ANOVA setups.
Best
Simon
-----------------------------------------
> dear simon.
>
> thanks for your advice about performing an anova for my question.
> unfortunately spm5 does not led me design one. maybe you know why?
> i've choosen the full factorial design and defined 2 factors
> (group (2
> levels) and time (4 levels)). this would be, from my perspective,
> a 2x4
> design, so i have to specify the con-files (each condition of my
> second
> session vs baseline condition) for 8 cells ([1 1], [1 2], [1 3],
> [1 4], [2
> 1], [2 2], [2 3], [2 4]).
> but spm gives me the following error message:
>
> Running "Factorial design specification"
> Error running job:
> Error using ==> spm_meanby
> row dimension mismatch between inputs
>
> did i miss something in the design? is my assumption of 8 cells wrong?
>
> sorry to bother you again.
>
> yours markus
>
>
-----------------------------------------------------------
Simon Eickhoff
Institut for Medicine (IME); Research Center Jülich
Leo-Brandt-Str. 5; 52425 Juelich, Germany
Phone + 49 2461-61-5219 / Fax + 49 2461-61-2820
e-mail: [log in to unmask] / [log in to unmask]
|