[Fieldtrip] design matrix (in)dependent sample t-test in ft_freqstatistics

[Nenad Polomac]

Dear Fildtripusers,

I have some time-freq EEG data from 2 Groups (25 Patients and 25 Controls).
There are 2 conditions in the paradigm. I would like to do dependent sample
t-test to compare conditions within Groups. Also I need  independent sample
t-test between the Groups. We have some preknowledge about the effects, so
we want to look in already defined sensors within certain frequency and
latency (no multiple comparison problem).

I have difficulties finding a solution for the design matrix in the
ft_freqstatistics.

I am not sure if this solution for dependent sample t-test is correct?
nsubj=25;
cfg.design=design(1,:) = [1:nsubj 1:nsubj];
cfg.design=design(2,:) = [ones(1,nsubj) ones(1,nsubj)*2];
uvar        = 1;
ivar        = 2;

For independent sample t-test I have no idea.I couldn't find solution on
the Tutorial Documentation page.

Any suggestion is greatly appreciated.

Thank you in advance!

Nenad

<https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=icon>
Virus-free.
www.avast.com
<https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=link>
<#m_-6583688795636336439_DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.haskell.org/pipermail/fieldtrip/attachments/20170222/65f9acc3/attachment.html>