[FieldTrip] degrees of freedom

Herring, J.D. (Jim) j.herring at fcdonders.ru.nl
Fri Jan 24 09:14:13 CET 2014

Hi Roy,


Fieldtrip allows you to create and use your own functions to calculate
statistics. What you could also do is adjust the indepsamplesT statistic
function (fieldtrip/statfun/ft_statfun_indepsamplesT.m) to suite your
needs (E.g. change the Df in line 89).  






From: fieldtrip-bounces at science.ru.nl
[mailto:fieldtrip-bounces at science.ru.nl] On Behalf Of Roy Cox
Sent: donderdag 23 januari 2014 16:20
To: fieldtrip at science.ru.nl
Subject: [FieldTrip] degrees of freedom


Hi all,

I'm using ft_timelockstatistics with indepsamplesT to compare spatial
topographies between two groups (n=15 and n=13). The measure I'm
interested in has no time dimension, so I basically have one sample per
electrode for each subject.


This works fine (I get the effects I hoped for). In order to make the
statistics 'slightly more valid', however, I need to adjust the degrees of
freedom. That is, the data I'm comparing between groups has already had a
covariate taken out. So df has to be df-1.

Doesn't look like Fieldtrip allows you to set this in the cfg struct
somewhere, so any suggestions where I need to hack?




Roy Cox, M.Sc. | Brain & Cognition Group | Department of Psychology |
University of Amsterdam | Weesperplein 4 | 1018 XA Amsterdam | the
Netherlands | room 3.21 | phone: +31 20 525 6847 | email: r.cox at uva.nl

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20140124/eaeeea4a/attachment-0002.html>

More information about the fieldtrip mailing list