Hi,
The within-group part sounds ok, yes, if you are getting a measure of
cross-subject variance then yes that corresponds to the mixed effects
variance when you run FEAT in OLS mode (ie not using FLAME).
Your "within-group" variance can be considered a within-subject fixed
effects variance, but this is directly estimated from the cross-
session variability, and ignores the within-session (time series)
variance, so will give the same FE variance as a FEAT analysis that
uses OLS and looks at cross-session variance, but will probably give
quite a different answer from a FLAME analysis which does use the
within-session variance.
Cheers, Steve.
On 30 Jan 2007, at 23:00, Vishwadeep Ahluwalia wrote:
> Hi,
> ive 21 subjects 4 runs each. I do an roi analysis using say
> amygdala... i
> record the mean Bold change within the roi for all subjects and all
> runs.
> Then using ANOVA on the 4 runs(using some stats software), one of the
> things i find is Mean Squares for within group and Mean Squares for
> between
> group. Is (MS)between group = Random Effect Variance and (MS)
> within group =
> Fixed Effect Variance as defined by FSL ..or am i completely
> delusional?
> Thanks!
>
> cheers,
> Vish
------------------------------------------------------------------------
---
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
------------------------------------------------------------------------
---
|