Hi,
On 27 Mar 2007, at 20:09, Steven Platek wrote:
> You wrote:
> Hi - I meant EV4 in the 2x2 factorial examplein the FEAT manual, i.e.
>
> the constant (group mean) EV.
>
> Cheers.
>
> How do I set this up in a repeated measures ANOVA? I tried adding
> the 4 columns to the end of my larger repeated measures design
> matrix, but i received an error message that the design was rank
> deficient.
I'm not quite sure which design we're talking about now, in any case
for either 1x4 or 2x2 you should have 3 EVs only for the ANOVA part
(as per the examples in the FEAT manual) and 17 (if you have 17
subjects) EVs for modelling out the subject means.
> I am not sure what I need to proceed with the 2 X 2 ANOVA analysis
> given that I have all of my first level "v. null" cope images in
> separate folders. That is if I set it up like the examle on the
> webpage replacing the 8 subjects with my 17, I then only have 17
> rows in the design matrix which does not allow me to enter the
> different levels of the design. I have 4 faces each at 2 levels.
> Should I reprocess at the first level including each of the 4 face
> stimuli v null in one feat directory?
It doesn't matter whether the lower-level copes are in separate FEAT
outputs or not - change the "inputs are FEAT directories" to "inputs
are copes" and change the number of inputs to 17x4=68 and then select
all 68 copes (you can use the paste method I sent in the first email
earlier).
Hopefully this should work fine then.
> Any help would be greatly appreciated.
>
> Also, on a different note, it appears for some studies the
> structurals (MP-RAGE) files are in the wrong orientation. Is there
> a way that I can correct the orientation in FSL?
The best thing is just to use avwswapdim to reorient them.
Cheers.
> Cheers, and thanks again.
>
> Steve
>
>
> ---
> Steven M. Platek, Ph.D.
> Associate and Managing Editor:
> Evolutionary Psychology
>
> Lecturer in Evolutionary Psychology
> School of Biological Sciences
> The University of Liverpool
> Liverpool
> L69 7ZB
>
> +44 (0) 151 795 4517
> +44 (0) 151 795 4408
> [log in to unmask]
>
> http://www.liv.ac.uk/evolpsyc/platek.html
> http://pcwww.liv.ac.uk/~splatek/
>
------------------------------------------------------------------------
---
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
------------------------------------------------------------------------
---
|