Print

Print


Hi - please see the TBSS manual - you should apply the GLM/correlation at the end using randomise.
Steve.


On 26 Mar 2012, at 10:17, SUBSCRIBE FSL Patricia Pires wrote:

Hello everyone!

I was wondering if you could help me with this analysis to my FA images in the Glm.
When I do a two sample unpaired t-test analysis i included two EV's one for each group. If i want to include a covariate (e.g. age) i included a third EV, etc.

I was wondering if there is any way to make correlations in the GLM. The way i am now correlating with FA data is extracting the average value of each image (fslmeants) and correlating this value with another feature (e.g. a score in a test) using SPSS. Is that way to correlate correct? or is there any better way to correlate maybe with glm in order to observe the image results of this correlation?

Thank you!

Patricia.



---------------------------------------------------------------------------
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
---------------------------------------------------------------------------