Dear Esa,
> After statistical analysis we got several significant brain regions.
> We used p=0.05 as a limit of statistical significance.
>
> Let's assume that the brain region with the biggest p-value is,
> say 0.05. That value is at lowest row of the result sheet.
> The other p-values are lower than 0.05.
>
> My question is about these lower ( more significant ) p-values.
> Can we interpret them as they are or can we only say that they
> are significant only at the 0.05 level and nothing more?
You can interpret them as they are.
>In other words would the lower p-values be same if the biggest p-value
>would be deleted?
Try this for yourself by raising the (height) threshold from P<0.05 to
something slightly higher (i.e. P<0.04). At the voxel level of inference,
you can see that the Z score and P values for the voxel of peak activation
in each blob remains the same. What changes is the size of the blobs,
because you are raising the overall threshold.
best wishes,
Geraint
------------------------------------------------------------------
Dr. Geraint Rees
Wellcome Advanced Fellow, Lecturer,
Mailstop 139-74, Institute of Neurology,
California Institute of Technology, University College London,
Pasadena, 12 Queen Square,
CA 91125 London WC1N 3BG
voice (626) 395-2880
fax (626) 796-8876
web http://www.klab.caltech.edu/~geraint
------------------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|