Hi Ajaay,
I believe that this value should not worry you. My understanding ist
that FDR is adaptive in the way that it finds the threshold from the
dataset, and if the criteria are not met, it will insert -Inf as the
threshold. You can check this by entering a progressively lower
threshold (i.e., higher p-value, say, 0.1/0.2/0.3...), and at some
point, results will appear. As to why it is more stringent than FWE in
your case, that is not unheard of and will depend on the dataset at hand
(but don't ask me exactly why :)
Cheers,
Marko
Ajay Kurani wrote:
> Hello SPM users,
> I have a quick question regarding the use of FDR correction when comparing a patient group to a control group using the VBM analysis. I am doing a two sample statistic and have enabled FDR correction by changing the defaults. I put .05 into FWE and again for FDR. I am concerned because when the results populate it shows T=6.566 for FWE of .05 and T = Inf for FDR of .05. This suggests to me that FDR is more stringent than FWE, which should not be the case. Can someone please explain if I am doing the procedure correclty?
>
>
> Results button --> SPM.mat file --> FWE or FDR button set to .05 --> Image appears with results
>
> In both cases we get null results which is ok, but it makes interpreting T = Inf difficult.
>
> Thanks,
>
> Ajay
>
--
____________________________________________________
PD Dr. med. Marko Wilke
Facharzt für Kinder- und Jugendmedizin
Leiter, Experimentelle Pädiatrische Neurobildgebung
Universitäts-Kinderklinik
Abt. III (Neuropädiatrie)
Marko Wilke, MD, PhD
Pediatrician
Head, Experimental Pediatric Neuroimaging
University Children's Hospital
Dept. III (Pediatric Neurology)
Hoppe-Seyler-Str. 1
D - 72076 Tübingen, Germany
Tel. +49 7071 29-83416
Fax +49 7071 29-5473
[log in to unmask]
http://www.medizin.uni-tuebingen.de/kinder/epn
____________________________________________________
|