Yes, sure – if, for example, you have to groups and the z-trasnformation is based on that smaple but you are analyzing only the data of one groups of subjects, i.e. a subsample, than your z-scores will have non-zero mean and you need to demean them.Smilarly, if your z-scores are derived from a normative sample which is not representative for your subjects you will end up with non-zero mean z-scores.Easy to check though, and I assume you z-transformed based on your sample.Cheers,AndreasVon: Stephen Smith <[log in to unmask]>Datum: Samstag, 8. Februar 2014 12:47
An: <[log in to unmask]>
Betreff: Re: [FSL] Demeaning with Z scores in GLM?
Well..... it's possible that the values might have been "turned into" z-scores separately from the selection of this particular sample of values, meaning that this particular set of values might not have mean zero - in which case yes it would be important to force the sample to have mean zero...Cheers.On 8 Feb 2014, at 11:45, Andreas Bartsch <[log in to unmask]> wrote:Hi,z-scores are already demeaned – the mean of all your z-scores is zero.No need to demean these again.Cheers,AndreasVon: Rosalia Dacosta Aguayo <[log in to unmask]>
Antworten an: FSL - FMRIB's Software Library <[log in to unmask]>
Datum: Samstag, 8. Februar 2014 11:18
An: <[log in to unmask]>
Betreff: [FSL] Demeaning with Z scores in GLM?
Dear FSL expertsI have a doubt about if it is necessary demean psychological scores with the GLM if they are Z scores rather than raw scores.With kind regards,Rosalia.
---------------------------------------------------------------------------
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve---------------------------------------------------------------------------Stop the cultural destruction of Tibet