Hi - yes, that's kind of opposite information - the more a data point is an outlier the more it will have a low weight (I think).

There's more info in the FSL course practical:
http://www.fmrib.ox.ac.uk/fslcourse/lectures/practicals/feat2/index.htm

Cheers.


On 1 Feb 2011, at 19:22, Xun Zhu wrote:

Hi,

  I am wondering what information the stats/weights1.nii.gz contains. It seems that the outliers have a significant small value in this 4D file but this it is slightly different from the prob_outlier1.nii.gz.

 Sorry for the question but unable to find any information elsewhere....

 Thank you!

Xun Zhu




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