Dear Artur,
> I just done the 2nd level analysis in SPM5 and I see that my design matrix
> has empty columns.
> I found some post on the list which are about that but still I am not sure
> If I did my design properly or that SPM5 allows such a design.
What have you tired?
Let me guess: it was a one-sample t-test! Correct?
In that case, the design-matrix basically has to look like that, since you want to test, whether the mean is significantly different from zero.
Now: take a look to an other design matrix. In most cases, you are modelling a global mean. This global mean, i.e. the mean across all time points, for example, is usually displayed as a long white column in your design matrix.
In case of a one-sample t-test, you are only interested in testing this mean. So, what do you think should be displayed in the design matrix? Bingo! Only a long white column. That's why it looks so empty, but it displays the correct design.
But, if you were trying something else than a one-sample t-test, than, of course, went something wrong.
Good luck,
Karsten
--
-------------------------------------------------------------
Karsten Specht, PhD
Department of Biological and Medical Psychology
& National Competence Centre for functional MRI
University of Bergen
Jonas Lies vei 91
5009 Bergen
Norway
Tel.: +47-555-86279
Fax: +47-555-89872
[log in to unmask]
http://fmri.uib.no/
|