I think this paper is a good review:
Neuroimage. 1999 Oct;10(4):483-6.
Ambiguous results in functional neuroimaging data analysis due to
covariate correlation.
Andrade A, Paradis AL, Rouquette S, Poline JB.
Dorian P. wrote:
> Dear all,
>
> In another thread it was explained that non-orthogonalized parametric
> modulators can loose the variance they have in common if they are
> collinear (in my case r = 0.47 or r = 0.67). Following this logic and
> trying to split the specific effects of two factors (strength of
> response/stimulus) I have removed the orthogonalization between the
> regressors of interest (keeping the orthogonalization with RTs and
> main condition). The results makes a lot of sense and seem reliable.
> But how can I cite this logic in a paper? I searched on the SPM
> bibliography but couldn't find any related title. Anybody knows a
> paper explaining how non-orthogonal correlated regressors compete for
> variance?
>
> Dorian
>
--
-------------------------------------------------------
Dr Richard Henson
MRC Cognition & Brain Sciences Unit
15 Chaucer Road
Cambridge
CB2 7EF, UK
Office: +44 (0)1223 355 294 x522
Mob: +44 (0)794 1377 345
Fax: +44 (0)1223 359 062
http://www.mrc-cbu.cam.ac.uk/people/rik.henson/personal
-------------------------------------------------------
|