Hello,
This error message does not apply to randomise and can safely be ignored.
Many Regards
Matthew
> Dear FSL experts,
>
> I want to run tbss analysis with randomise comapring 2 groups, each groups has pre-post scans.
> I found an example of such design in the forum in -"tbss longitudinal study" form may 2010.
> https://www.jiscmail.ac.uk/cgi-bin/webadmin?A2=ind1005&L=FSL&F=&S=&X=57C5C459853A5E825D&Y=shir_hof%40yahoo.com&P=363532
> I used the same design: 1 ev for each group, 1 ev for each subject, and an exchaneability block specifying subjects number.
>
> However, when trying to view the design or save it I recieve the following error message:
> "Problem with processing the model: Warning - design matrix uses different groups (for different variances), but these do not contain "separable" EVs for the different groups (it is necessary that, for each EV, only one of the groups has non-zero values).
>
> What can be the problem? Is the design.grp wrong?
>
> Many thanks for your help,
> shir
>
|