Hi
--------------------
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington,
Oxford. OX3 9 DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask]
http://www.fmrib.ox.ac.uk/~steve
----------------------
On 19 Sep 2012, at 09:47, "SUBSCRIBE FSL B. Jeong" <[log in to unmask]> wrote:
> Thank you for your response!
>
> I got two errors (slices_summary, nets_lda) and have one question about the output from nets_glm.
>
> 1. I can not find slices_summary.m.
It's an FSL script - you need FSL5
>
> 2. And, I got other error messages in nets_lda
>
>>> [lda_percentages]=nets_lda(netmat1,28)
> ??? Reference to non-existent field 'GroupNames'.
>
> Error in ==> svmclassify at 90
> groupnames = svmStruct.GroupNames;
>
> Error in ==> nets_lda at 61
> lda(7,n)=svmclassify(svmstruct,xx')*2-1; % SVM
>
See wiki doc wrt which matlab toolboxes you need.
>
> 3. In terms of the output for contrast 1, nothing was survived after correction for multiple comparison (FWE, FDR). But in p_corrected I can find several lower than 0.05 and can see several color boxed in figure. Is the value of p_corrected 1-P, not p value itself?
Can't remember.....on train.....check source!
>
>>> [p_uncorrected,p_corrected]=nets_glm(netmat1,'design.mat','design.con',1);
>
> .....
>
> ans =
>
> contrast 1, best values: uncorrected_p=0.017200 FWE_corrected_p=0.702200.
> FDR-correction-threshold=0.000000 (to be applied to uncorrected p-values)
>
>
> ans =
>
> contrast 2, best values: uncorrected_p=0.000400 FWE_corrected_p=0.005600.
> FDR-correction-threshold=0.000400 (to be applied to uncorrected p-values)
>
>>> p_corrected(2,:)
>
> ans =
>
> Columns 1 through 11
>
> 0 0.0498 0.3434 0 0 0 0 0.0008 0 0 0
>
> Columns 12 through 22
>
> 0 0 0.0498 0 0 0 0 0.0096 0 0.1148 0
>
>
>
|