Dear Peter,
"nuisance" covariates are treated as any covariates. If you want to treat
them as nuisance, just do not test them with contrasts. Otherwise, there
is nothing special or magic about them.
Hope this helps,
Volkmar
On Tue, 26 Sep 2006, Peter Nestor wrote:
> Dear Volkmar
> A supplementary question. WHere is the 'intended' place for nuisance
> covariates in SMP5? Something that is not at all obvious cf earlier versions
> of SPM.
> Peter Nestor
>
> On 26 Sep 2006, at 08:33, Volkmar Glauche wrote:
>
> > On Tue, 26 Sep 2006, Oliver Singer wrote:
> >
> > > I have a rather basic question: I want to run a simple regression
> > > between
> > > structural images (T1) and an electrophysiological parameter as
> > > covariate in
> > > SPM5. When choosing "2nd level analysis" and "multiple regression"
> > > there are
> > > two options to enter "covariates", either directly under the
> > > "multiple
> > > regression" option or under the "design" option. I am wondering which
> > > one is
> > > the appropriate to choose...
> >
> > Actually, this should not really matter - but the option below the
> > "design" is intended to be the correct place.
> >
> > Volkmar
> >
> > --
> > Volkmar Glauche
> > -
> > Department of Neurology [log in to unmask]
> > Universitaetsklinikum Freiburg Phone 49(0)761-270-5331
> > Breisacher Str. 64 Fax 49(0)761-270-5416
> > 79106 Freiburg http://fbi.uniklinik-freiburg.de/
> >
>
>
--
Volkmar Glauche
-
Department of Neurology [log in to unmask]
Universitaetsklinikum Freiburg Phone 49(0)761-270-5331
Breisacher Str. 64 Fax 49(0)761-270-5416
79106 Freiburg http://fbi.uniklinik-freiburg.de/
|