Anna
If the covariate for that condition were orthogonal to all
other covariates in your first model, the parameter estimates
for that condition would be the same in both models. The p-values
associated with that parameter estimate however (for the [0 0 1 0 0]
and [1] contrasts) would differ as a function of the different
degrees of freedom and different residual errors in the two models.
Rik
Anna Sterkin wrote:
>
> Dear spm experts,
>
> I have the following question:
>
> In the case of a study design with 5 different conditions in
> each session we are interested to see the activation for every
> single condition separately, and afterwards for different
> combinations of conditions. In other words, in our study we
> want to see the active voxels for condition number 3, and
> ignore the other four conditions (don't care).
> For this we define the following contrast: [0 0 1 0 0].
> Is the result of the statistical calculations with this
> contrast the same as if we would use a model for a single
> condition number 3 alone in a session against baseline: [1]?
>
> Thank you,
>
> Anna Sterkin.
--
---------------------------8-{)}-------------------------
DR R HENSON
Wellcome Department of Cognitive Neurology
12 Queen Square
London, WC1N 3BG
England
EMAIL: [log in to unmask]
URL: http://www.psychol.ucl.ac.uk/rik.henson/index.html
TEL1 +44 (0)20 7833 7483
TEL2 +44 (0)20 7833 7472
FAX +44 (0)20 7813 1420
---------------------------------------------------------
--
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|