Hello Donald and Simon,
the reason for analyzing such mean-centered data is that I need to
estimate the maximum value of my statistics within the analysis mask
under the null hypothesis of no condition effect. This involves a
resampling scheme (I am referring to the bootstrap-F principle): the
FWE-corrected p-value of the statistic computed with unaltered data can
be computed from the observed distribution of the maximum statistics
across analyses of resampled mean-centered data (percentile method).
Donald: I tried adding a constant, it did not help, and disabling
sphericity corrections and assuming independence is not a good idea.
I am thinking that the correct approach here would be to consider the
ResMS and variance estimates from the unaltered data, and plug in those
when analyzing the mean-corrected data. It is not obvious if this would
be enough (e.g., should I consider eventual whitening? I am not 100%
familiar with the mechanics).
Thank you for your thoughts,
Bruno
On 14/05/2012 4:46 PM, MCLAREN, Donald wrote:
> What you want to do is to disable the REML estimation (e.g
> non-sphericity correction) OR setup the model to assume that everything
> is independent (this sets the covariance to 0). Of course, the latter
> option is bad for of obvious reasons.
>
> An alternative might be to add 1 to all the input images. The issue then
> becomes how to subtract out the 1 from the betas to make the contrasts
> test things agaisnt 0. If you are comparing conditions, the added 1 to
> all images should have no effect on the statistics. This should find the
> significant voxels for REML estimation as well.
>
> Best Regards, Donald McLaren
> =================
> D.G. McLaren, Ph.D.
> Postdoctoral Research Fellow, GRECC, Bedford VA
> Research Fellow, Department of Neurology, Massachusetts General Hospital
> and
> Harvard Medical School
> Website: http://www.martinos.org/~mclaren
> <http://www.martinos.org/%7Emclaren>
> 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 Mon, May 14, 2012 at 11:40 AM, Eickhoff, Simon
> <[log in to unmask] <mailto:[log in to unmask]>> wrote:
>
> Dear Bruno
>
>
> The problem you encounter may relate to the fact, that only voxels
> passing an F-threshold of p<0.001 (spm_spm ~ line 450), i.e., those
> voxels where your model fits reasonably well, enter the
> non-sphericity estimation (cf. ~ line 700).
>
> If the analysis crashed with an "no inmask voxels", that should be
> the reason (your noise-model didn't fit anywhere)
>
>
> If the analysis ran through but you got "no significant voxels" in
> the inference... this is exactly what happend: Nothing was
> significant, which is not surprising given you only entered noise.
>
> It's not clear to me, however, why you would want to fit that model
> anyways, given you know the mean and variance of your data since you
> actually generated it from a particular generative model.
>
>
> Best
> Simon
>
>
>
>
> ________________________________________
> Von: SPM (Statistical Parametric Mapping) [[log in to unmask]
> <mailto:[log in to unmask]>]" im Auftrag von "Bruno L.
> Giordano [[log in to unmask] <mailto:[log in to unmask]>]
> Gesendet: Montag, 14. Mai 2012 17:00
> An: [log in to unmask] <mailto:[log in to unmask]>
> Betreff: [SPM] Estimating a second-level model under the null hypothesis
>
> Dear list,
>
> I am trying to fit a null model second level model where the
> across-subjects mean of each condition is set to 0. I need the parameter
> estimates for resampling under H0 of no between-condition difference.
> SPM protests that I have no significant voxel. I would need the
> estimates/stats anyways.
>
> What could I do?
>
> Thank you,
>
> Bruno
>
>
> ------------------------------------------------------------------------------------------------
> ------------------------------------------------------------------------------------------------
> Forschungszentrum Juelich GmbH
> 52425 Juelich
> Sitz der Gesellschaft: Juelich
> Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498
> Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher
> Geschaeftsfuehrung: Prof. Dr. Achim Bachem (Vorsitzender),
> Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt,
> Prof. Dr. Sebastian M. Schmidt
> ------------------------------------------------------------------------------------------------
> ------------------------------------------------------------------------------------------------
>
> Kennen Sie schon unseren neuen Film? http://www.fz-juelich.de/film
> Kennen Sie schon unsere app? http://www.fz-juelich.de/app
>
>
|
