Dear Gaby,
yes, this is to be expected, because SPM will fit your entire model at
once to the data, without orthogonalising your covariates. If you want to
decorrelate them, you need to do this before entering them into SPM.
Volkmar
On Mon, 19 Mar 2007, Gaby Pell wrote:
> Dear all,
>
> I am attempting a regression analysis with a number of covariate columns.
> I am not finding a difference in the results when I manipulate the order
> that the covariates are arranged in the design matrix even if the
> covariates are highly correlated with each other. Is this to be expected?
>
> Yours sincerely,
>
> Gaby
>
> ***************************************
> Gaby Pell, PhD
> Brain Research Institute
> Ground Floor, Neurosciences Building
> Austin Health
> Banksia Street
> West Heidelberg,
> Melbourne,
> Victoria, 3081
> Australia
> Tel: (+61 3) 9496-2868 (W)
> Tel: (+61 3) 9523-5883 (H)
> Fax: (+61 3) 9496-4071 (W)
> Email: [log in to unmask]
>
>
>
--
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/
|