hi Nick, yes I did - zscore(ds, chunks_attr=‘task’) (I am training the classifier on task 1 and then testing on task 2, and zscoring done within each one) cheers ds
On Fri, Aug 8, 2014 at 5:36 PM, Nick Oosterhof <[email protected]> wrote: > On Aug 8, 2014, at 5:55 PM, David Soto <[email protected]> wrote: > > > Thanks for the response, yes I tried to do a cross-subjects > classification > > and got some results but looked noisy (0.58 classification accuracy > > only on some voxels following a whole brain search light)....however in > the univariate > > FEAT GLM I get robust activations which overlap spatially across the > different conditions. > > Did you normalize the data (e.g. z-scoring)? Please see my previous > message for why that could be useful. > > _______________________________________________ > Pkg-ExpPsy-PyMVPA mailing list > [email protected] > http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa > -- http://www1.imperial.ac.uk/medicine/people/d.soto/
_______________________________________________ Pkg-ExpPsy-PyMVPA mailing list [email protected] http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
