Hi Christian!
> did you use quadratic modeling? Then the behavior might be due to and inherent unidentifiability of quadratic models, although this should
> only affect two types of models.
Well, we tested 4 bilinear and 2 quadratic models. What we observed was, that DCM.F was exactly the same for the 4 bilinear models and also exactly the same (but slightly different to the bilinear ones) for the 2 quadratic models.
> In a bilinear model this seems rather strange and I don't have an answer to that one but I'll think about it.
This was also my feeling, which is why I posted this problem I never encountered before.
> One more question: since you mentioned the residuals in Z were identical, what about X and Y, although I assume that if F is equal
> those should be equal too.
Those are equal, but they should be, as X is in both (all) cases only driven by x while Y is only driven by y and both both only feature feed-forward connections to Z. So if the residuals differed, this would be strage. Moreover, the driving inputs (DCM.C) are estimated almost exactly identically, so there could not be any difference.
Still clueless...
Best
Simon
>
> regards
> Christian Kasess
>
> Eickhoff, Simon wrote:
> > Dear Christian
> >
> >
> > For the RDFX or FFX model comparison, this may be a good explanation.
> > And in fact, we see identical posterior evidence here.
> >
> > But what I'm most puzzled by is the fact, that for each individual
> > model the evidence as stored in DCM.F is exactly identical even though
> > the models are clearly different and the parameters look reasonable.
> >
> >
> > Best
> > Simon
> >
> >
> > ------------------------------------------------------------------------
> > *Von:* Grefkes, Dr. Christian [[log in to unmask]]
> > *Gesendet:* Donnerstag, 4. Februar 2010 14:29
> > *An:* Eickhoff, Simon; [log in to unmask]
> > *Betreff:* Re: [SPM] Strange behaviour of model evidence
> >
> > Dear Simon!
> >
> >
> >
> > We encountered a similar problem some weeks ago when comparing 10 DCMs
> > with different connectivity patterns. After extensive testing we found
> > out that this strange result was caused by the inclusion of one
> > particular model. When we removed this model from our sample of DCMs,
> > we got reasonable results. Interstingly, this problem only occured for
> > a random-effects approach but not for a fixed-effects analysis. But I
> > still don't have an explanation for this...
> >
> >
> >
> > Best wishes,
> >
> > Christian
> >
> >
> >
> >
> >
> > --------------------------------------------------
> > Dr. med. Christian Grefkes
> >
> > Klinik und Poliklinik für Neurologie
> > Universität zu Köln
> > Kerpener Straße 62, 50924 Köln
> > phone: +49-221-4726-310
> > fax: +49-221-478-7005
> > http://cms.uk-koeln.de/neurologie/content/mitarbeiter/index_ger.html
> >
> >
> > Max Planck Institute for Neurological Research
> > Research Group Leader
> > Neuromodulation & Neurorehabilitation
> > Gleueler Str. 50, 50931 Köln
> > phone: +49-221-4726-310
> > fax: +49-221-4726-298
> > http://www.nf.mpg.de/index.php?id=255
> >
> >
> >
> >
> >
> > "Eickhoff, Simon" <[log in to unmask]> hat am 4. Februar 2010 um
> > 14:05 geschrieben:
> >
> > > Dear Klaas and DCM-experts
> > >
> > >
> > > Recently, we encountered what we considered a rather strange
> > behaviour of model evidence in DCM for fMRI (SPM8):
> > >
> > > We tried to explain an (positive) interaction observed in the GLM
> > analysis of a 2x2 design in region Z by different models of
> > feed-forward from the two regions [X, Y] showing the main effects for
> > the two factors [x and y].
> > >
> > > So we set up and estimated several model.
> > >
> > > In all models, the values obtained for the different parameters
> > (driving input, intrinsic connections and modulations) were well
> > plausible.
> > >
> > >
> > > Strangely, however, the model evidence DCM.F as well as AIC/BIC is
> > exactly (!) identical across models.
> > >
> > > Closer analysis showed, that in spite of the different connection
> > patterns (e.g., different patterns of modulation such as X->Z
> > modulated by y or Y->Z modulated by x) and the plausible parameters
> > (in the range of 0.01 to 0.1), the residuals in Z were basically
> > identical.
> > >
> > >
> > > Any thoughts on this? Seems not logical to me!
> > >
> > > Thanks in advance
> > > Simon
> > >
> > >
> > ------------------------------------------------------------------------------------------------
> > >
> > ------------------------------------------------------------------------------------------------
> > > Forschungszentrum Juelich GmbH
> > > 52425 Juelich
> > > Sitz der Gesellschaft: Juelich
> > > Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498
> > > Vorsitzende des Aufsichtsrats: MinDir'in Baerbel Brumme-Bothe
> > > Geschaeftsfuehrung: Prof. Dr. Achim Bachem (Vorsitzender),
> > > Dr. Ulrich Krafft (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt,
> > > Prof. Dr. Sebastian M. Schmidt
> > >
> > ------------------------------------------------------------------------------------------------
> > >
> > ------------------------------------------------------------------------------------------------
>
>
> --
> Christian H. Kasess
> Zentrum f.Biomed. Technik und Physik MR Center of Excellence
> Medizinische Universitaet Wien AKH-Wien
> Waehringerstrasse 13 Lazarettgasse 14
> A-1090 Vienna, AUSTRIA A-1090 Vienna, AUSTRIA
> Tel: +43-1-40400-1793
> Fax: +43-1-40400-7631
> http://www.meduniwien.ac.at/hochfeld-mr/
>
--
===================================
Univ.-Prof. Dr. med. Simon B. Eickhoff
AG Neuropsychiatrische Systembiologie
Klinik für Psychiatrie und Psychotherapie
Universitätsklinikum Aachen
Telefon: +49 241 80 80523
Fax: +49 2461 61 2820
eMail: [log in to unmask]
und
Institut für Neurowissenschaften und Medizin
Forschungszentrum Juelich
Telefon: +49 2461 61 8609
Fax: +49 2461 61 2820
eMail: [log in to unmask]
|