[Eeglablist] 2x2 design statcondfieldtrip

[Andreas Widmann]

How to do this with Fieldtrip is described in detail here:
http://www.fieldtriptoolbox.org/faq/how_can_i_test_an_interaction_effect_using_cluster-based_permutation_tests

Maybe this approach also works in EEGLAB?

Best,
Andreas

> Am 30.03.2016 um 11:20 schrieb Noordenbos, M.W. (Mark) <m.noordenbos at let.ru.nl>:
> 
> 
> Hi EEGlablist,
> 
> I have a 2x2 design (2 groups x 2 conditions) for which I would like to calculate the interaction effect, so I can test whether the effect in each group is also significantly different. In the code of statcondfieldtrip function I found an option to perform a two-way ANOVA using the function ‘anovan’ for the ‘X1*X2’ effect. But it seems that this part of the code is not (yet) implemented/working. 
> 
> I tried the following test code, but ft_freqstatistics (Fieldtrip function) cannot handle the input for the anovan function.
> 
> n = 1000;
> nchan = 61;
> 
> dat = { rand(n,nchan) rand(n,nchan); rand(n,nchan) rand(n,nchan) };
> 
> [ori_vals, df, pvals] = statcondfieldtrip(dat, ‘paired’, ‘on’)
> 
> Does anyone know how to perform this two-way anova using the anovan function in combination with the multiple comparison correction of Fieldtrip? Or whether there is a workaround to make the statcondfieldtrip function work for a two-way anova?
> 
> Thanks,
> Mark
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to eeglablist-request at sccn.ucsd.edu