Hi, yes the varcope is computed from the residuals, using the formula:
var(c' b)=c' pX AVA' pX' c sigsq
where
c' is the contrast vector
b is the estimated effect size (beta or pe)
pX is the pinv of the design matrix
AVA' is the covariance/whitening
sigsq is the estimate of the residuals
Cheers, Steve.
On Mon, 14 Jun 2004, SUBSCRIBE FSL Zhang, X wrote:
> Dear FSL experts:
> I thought GLM formular only yields one residual array
> data-sum(pe*design matrix) = residual (number of volumes by 1 array)
> how can we get a varcope for every contrast? could you tell me what
> is the formula to get a varcope for a particular contrast?
> Appreciate your help
>
> yours Xian
>
Stephen M. Smith DPhil
Associate Director, FMRIB and Analysis Research Coordinator
Oxford University Centre for Functional MRI of the Brain
John Radcliffe Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
|