[FieldTrip] statfun_depsamplesregrT

[Marcin]

Dear Dr. Maris,

thanks for your reply.
If I get you right you say that whether I use the statfun_depsamplesregrT
or use/write statfun_depsamplesrankcorr depends on assumed (apriori)
relation between the predictor variable (experimental condition) and the
data. If I assume linearity (i.e. in the case of WM load:  ERP/TF(1) <
ERP/TF(2) < ERP/TF(3) < ERP/TF(4)) I might use the statfun_depsamplesregrT.
If I doubt linearity (i.e.WM load ERP/TF(1) < ERP/TF(2) <= ERP/TF(3) <
ERP/TF(4)) I should use the statfun_depsamplesrankcorr. Is this correct?

I am not sure if I underestood your point about reference distribution. Are
you saying that for the cluster-based permutation inference I need to
threshold on a reference distribution which might be either parametric or
non-parametric? If this is the case. What does it depend on whether I use
parametric or non parametric reference distribution?

Thank you again for your time and your help.

Best,
Marcin

W dniu 22 marca 2012 21:12 użytkownik Eric Maris <e.maris at psych.ru.nl>napisał:

> Dear Marcin,****
>
> ** **
>
> ** **
>
> The statfun_depsamplesregrT calculates a T-statistic for regression
> coefficients that are calculated within each of the units-of-observation
> (typically, participants) obtained by regressing the subject-specific data
> (spatiotemporal, spatio-spectral, spatio-spectro-temporal) on some
> predictor variable that varies over the different conditions in which this
> participant has provided data (e.g., working-memory load, retention
> interval, luminance, contrast, etc). If you doubt the assumed linear
> relation between predictor variable and biological data, then you could
> write your own statfun_depsamplesrankcorr. To use this test statistic for
> cluster-based permutation inference, you need a threshold based on some
> reference distribution (which can be parametric, but must not be). ****
>
> ** **
>
> To get this statfun_depsamplesrankcorr running, you will probably have to
> take a look in the Fieldtrip code to see how the statistics framework is
> structured.****
>
> ** **
>
> Best,****
>
> ** **
>
> Eric Maris****
>
> ** **
>
> ** **
>
> *From:* Marcin [mailto:m.leszczynski.m at googlemail.com]
> *Sent:* woensdag 21 maart 2012 10:51
> *To:* Email discussion list for the FieldTrip project
> *Subject:* [FieldTrip] statfun_depsamplesregrT****
>
> ** **
>
> Dear Fieldtripers,
>
> Could anyone explain me what is being calculated with the
> statfun_depsamplesregrT function, please.
>
> David Groppe (thank you David) suggested in a previous thread on the list
> that I might calculate permutation test based on rank correlation to
> account for monotonic relationships within the permutation framework. I was
> wondering if this is the kind of test that statfun_depsamplesregrT function
> calculates.
> http://mailman.science.ru.nl/pipermail/fieldtrip/2011-December/004578.html
>
> Best,
> Marcin****
>
> _______________________________________________
> fieldtrip mailing list
> fieldtrip at donders.ru.nl
> http://mailman.science.ru.nl/mailman/listinfo/fieldtrip
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20120328/e5278c6c/attachment-0002.html>