Marko,

You are right -- if the correct cluster P-value is larger than the uncorrected cluster P-value, then this is an issue and shouldn't be happening. I misinterpreted the email as the next line asks about peak values. 

On Tue, Jun 9, 2015 at 9:08 AM, Marko Wilke <[log in to unmask]> wrote:

Hi,

but wasn't the question whether uncorrected *cluster-level* p-values can be higher than corrected cluster-level ones? I think the culprit here may be in the ROI/SVC approach, which may mess with the smoothness estimation, depending on how it is done. Perhaps you, Sara, could provide some more details about how you set up your analyses?

Cheers
Marko

MCLAREN, Donald wrote:

Yes. The cluster statistics are always weaker than the individual voxel
significance. I prefer to look at the cluster significance as I don't
believe that the brain would only have differential
activity/connectivity/volume/etc. in a single isolated voxel.

Best Regards, Donald McLaren
=================
D.G. McLaren, Ph.D.
Research Fellow, Department of Neurology, Massachusetts General Hospital and
Harvard Medical School
Postdoctoral Research Fellow, GRECC, Bedford VA
Website: http://www.martinos.org/~mclaren
Office: (773) 406-2464
=====================
This e-mail contains CONFIDENTIAL INFORMATION which may contain PROTECTED
HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED and which is
intended only for the use of the individual or entity named above. If the
reader of the e-mail is not the intended recipient or the employee or agent
responsible for delivering it to the intended recipient, you are hereby
notified that you are in possession of confidential and privileged
information. Any unauthorized use, disclosure, copying or the taking of any
action in reliance on the contents of this information is strictly
prohibited and may be unlawful. If you have received this e-mail
unintentionally, please immediately notify the sender via telephone at (773)
406-2464 or email.

On Tue, Jun 9, 2015 at 7:03 AM, Sara Garofalo <[log in to unmask]

<mailto:[log in to unmask]>> wrote:

    Hi all,

    I have some (supposedly) strange results regarding an ROI analysis
    using small volume correction. When looking at cluster-level
    statistics the _uncorrected_ p-value is _not significant_ (e.g.,
    p=.12), while the FEW _corrected_ p-value is _significant_ (e.g.,
    p=.001). Does that make any sense?

    Is it more correct to only look at peak-level statistics?

    Many many thanks,

    Sara

--
____________________________________________________
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/
____________________________________________________