|
Hi Ben
If you look at the regressors for the attention
dataset sometimes all three effects are present, there
is overlap. You have taken your first regressor and
divided it up so you can obtain your first regressor
by adding the others together. What you would usually
do I think is specify your design matrix without the
first one and specify a contrast based on all other
regressors as being equivalent to the first. Are you
using all of those regressors to specify your DCM? Can
you leave any out?
Hope this helps
Nia
--- "Xu, Ben (NIH/NINDS) [E]" <[log in to unmask]>
wrote:
> Nia,
>
> I have tried the "attention" data and looked at the
> effect of each
> regressor in Results. I did not subtraction of one
> regressor from the
> other. But, it allowed me to look at the effect of
> each regressor itself
> (i.e., t-contrast between the regressor and the
> implicit baseline, I
> think). But, this won't work with my design matrix.
> Also, can you tell
> me why the "attention" matrix did not have the
> warning "not uniquely
> specified?"
>
> I'm asking the question because the DCM estimate for
> my dataset ran well
> (i.e., no error message) while there is some oddity
> in the results. I'd
> like to know if there is anything to do with my
> design matrix. I can't
> see any difference between the first regressor
> modeled in my matrix and
> that in the "attention' dataset.
>
> Thanks much.
>
> Ben
>
> -----Original Message-----
> From: Nia Goulden [mailto:[log in to unmask]]
> Sent: Thursday, August 17, 2006 10:07 AM
> To: [log in to unmask]
> Subject: Re: [SPM] DCM design matrix
>
> Hi Ben
>
> In the attention dataset I don't think that you can
> add/subtract any two regressors and get the other
> regressor as a result, they are independent.
>
> Nia
>
>
> --- "Xu, Ben (NIH/NINDS) [E]" <[log in to unmask]>
> wrote:
>
> > Thanks, Nia, for your quick response. But, isn't
> > this how one creates
> > the "input" regressor for DCM? (see the attached
> > design matrix for the
> > "attention" data.)
> >
> > Ben
> >
> > -----Original Message-----
> > From: Nia Goulden [mailto:[log in to unmask]]
> > Sent: Thursday, August 17, 2006 9:39 AM
> > To: [log in to unmask]
> > Subject: Re: [SPM] DCM design matrix
> >
> > Hi Ben
> >
> > I think the error you're getting is telling you
> that
> > your first regressor is a linear combination of
> > regressors 2,3,4 and 5 i.e. when you put these
> > regressors together then you get the first
> > regressor.
> > The regressors are therefore not independent.
> >
> > Hope this helps
> > Nia
> >
> >
> > --- "Xu, Ben (NIH/NINDS) [E]"
> <[log in to unmask]>
> > wrote:
> >
> > > Hi,
> > >
> > > I have asked the question earlier but have not
> > > gotten a response. I'm
> > > trying to use DCM for an fMRI study and have a
> > > question related to the
> > > design matrix prior to DCM analysis.
> > >
> > > I created a design matrix (attached) with 7
> > > regressors (i.e.,
> > > conditions) and an implicit baseline. The 1st
> > > regressor shares common
> > > input with regressor 2-5, and will be used for
> the
> > > "input drive" to the
> > > intrinsic connections. (Regressors 6-7 will not
> be
> > > included in the DCM
> > > analysis.)
> > >
> > > Questions:
> > > 1. As I understand, it's ok to have a
> > non-orthogonal
> > > design matrix for
> > > DCM analysis. Is that correct?
> > >
> > > 2. The design matrix indicates regressors 1-5
> are
> > > "not uniquely
> > > specified" and, therefore I can't define
> contrasts
> > > in "Results." I have
> > > tried the "attention" dataset provided at the
> SPM
> > > Web site
> > > (http://www.fil.ion.ucl.ac.uk/spm/data/). Its
> > design
> > > matrix is
> > > non-orthogonal, either. However, there is no
> > warning
> > > on regressors "not
> > > uniquely specified." And it allows t contrasts
> in
> > > Results. What's wrong
> > > with my design? Will it affect the DCM analysis?
> > >
> > > Any help is greatly appreciated.
> > >
> > > Ben
> > >
> >
> >
> >
> >
> >
>
___________________________________________________________
> >
> > Copy addresses and emails from any email account
> to
> > Yahoo! Mail - quick,
> > easy and free.
> > http://uk.docs.yahoo.com/trueswitch2.html
> >
>
>
>
>
>
___________________________________________________________
>
> The all-new Yahoo! Mail goes wherever you go - free
> your email address
> from your Internet provider.
> http://uk.docs.yahoo.com/nowyoucan.html
>
___________________________________________________________
Inbox full of spam? Get leading spam protection and 1GB storage with All New Yahoo! Mail. http://uk.docs.yahoo.com/nowyoucan.html
|
