[FieldTrip] testing if power is significantly different from zero

"Jörn M. Horschig" jm.horschig at donders.ru.nl
Thu Jul 17 16:43:34 CEST 2014


Hey,

I actually wouldn't advise to test power against 0. Since power is a 
positive measure (bound to 0), noise will cumulatatively add up and your 
test against 0 will effectively check whether you recorded something 
(aka noise) or not. But, as Nietzsche said, you can ask whether your 
measured powered is significantly different from 0 using her approach. 
It's just not a very clever question to ask... ;)

Best,
Jörn


On 7/17/2014 3:45 PM, Constantino Méndez Bértolo wrote:
> Bump,
> wishing that some sage fieldtripper either back-up the "t-test against 
> homologue data filled with zeros method" or suggests a better approach,
> thx
>
>
> 2014-07-17 13:56 GMT+02:00 Lam, Nietzsche <n.lam at fcdonders.ru.nl 
> <mailto:n.lam at fcdonders.ru.nl>>:
>
>     Hi Hweeling,
>
>     I think the approach is similar to testing two different
>     conditions. I have a suggestion below, but I think some people
>     would argue that this is not a good way to do the test.
>
>      You can keep the design matrix the same as comparing two
>     conditions, but for the "zero" condition, you will turn this all
>     into zeros.
>     dat1.powspctrm = %power from your condition of interest
>     dat2 = dat1      % your "zero" condition"
>     dat2.powspctrm(:) = 0; % making the data structure identical to
>     condition of interest but everything is zero.
>     Then call your statistics function as before.
>
>     Perhaps someone else can give you more detail on this.
>
>     Nietzsche
>
>     ----- Original Message -----
>     > From: "Hwee Ling Lee" <hweeling.lee at gmail.com
>     <mailto:hweeling.lee at gmail.com>>
>     > To: "FieldTrip discussion list" <fieldtrip at science.ru.nl
>     <mailto:fieldtrip at science.ru.nl>>
>     > Sent: Thursday, 17 July, 2014 1:26:59 PM
>     > Subject: [FieldTrip] testing if power is significantly different
>     from zero
>     > Hi all,
>     >
>     >
>     > I have a naive question regarding cluster statistics in fieldtrip.
>     >
>     >
>     > Is it possible to run a statistical analysis to test if power is
>     > significantly different from zero? If so, how do I build the design
>     > matrix for this case?
>     >
>     >
>     > Thanks.
>     >
>     >
>     > Cheers,
>     > Hweeling
>     >
>     >
>     > _______________________________________________
>     > fieldtrip mailing list
>     > fieldtrip at donders.ru.nl <mailto:fieldtrip at donders.ru.nl>
>     > http://mailman.science.ru.nl/mailman/listinfo/fieldtrip
>
>     --
>     Nietzsche H.L. Lam, MSc
>     PhD Candidate
>
>     Max Planck Institute for Psycholinguistics
>     Wundtlaan 1, 6525 XD Nijmegen, The Netherlands
>
>     Donders Institute for Brain, Cognition and Behaviour,
>     Centre for Cognitive Neuroimaging,
>     Kapittelweg 29, 6525EN Nijmegen, The Netherlands
>
>     n.lam at fcdonders.ru.nl <mailto:n.lam at fcdonders.ru.nl>
>     +31-24-3668219 <tel:%2B31-24-3668219>
>
>
>     neurobiologyoflanguage.com <http://neurobiologyoflanguage.com>
>     _______________________________________________
>     fieldtrip mailing list
>     fieldtrip at donders.ru.nl <mailto:fieldtrip at donders.ru.nl>
>     http://mailman.science.ru.nl/mailman/listinfo/fieldtrip
>
>
>
>
> -- 
> Constantino Méndez-Bértolo
> Laboratorio de Neurociencia Clínica,Centro de Tecnología Biomédica (CTB)
>
> Parque Científico y Tecnológico de la UPM, Campus de Montegancedo
>
> 28223 Pozuelo deAlarcón, Madrid, SPAIN
>
>
>
>
> _______________________________________________
> fieldtrip mailing list
> fieldtrip at donders.ru.nl
> http://mailman.science.ru.nl/mailman/listinfo/fieldtrip


-- 
Jörn M. Horschig
PhD Student
Donders Institute for Brain, Cognition and Behaviour
Centre for Cognitive Neuroimaging
Radboud University Nijmegen
Neuronal Oscillations Group
FieldTrip Development Team

P.O. Box 9101
NL-6500 HB Nijmegen
The Netherlands

Contact:
E-Mail: jm.horschig at donders.ru.nl
Tel:    +31-(0)24-36-68493
Web: http://www.ru.nl/donders

Visiting address:
Trigon, room 2.30
Kapittelweg 29
NL-6525 EN Nijmegen
The Netherlands




More information about the fieldtrip mailing list