[Eeglablist] statcondfieldtrip for cluster-based nonparametric/permutation testing

Arnaud Delorme arno at ucsd.edu
Mon Feb 25 07:10:37 PST 2019


Dear Taylor,

Fieldtrip does not support n x m designs (2-way Anovas) only one way designs. I assume you want to use the cluster correction for multiple comparisons. For this, you would need to use LIMO functions or Mass Univariate Toolbox functions.

Best wishes,

Arno

> On Feb 24, 2019, at 3:12 PM, Taylor Hearn <thearn at asu.edu> wrote:
> 
> Hi Everyone,
> 
> I am trying to use the "statcondfieldtrip" function to analyze time-series and time/frequency event-related potentials, and I am looking for some assistance. When I attempt to run  "statcondfieldtrip" I get the following error: Error using ft_freqstatistics (line 177) the length of the design matrix (3) does not match the number of observations in the data (6).
> 
> My data is organized as a 2x3 cell (2 conditions and 3 groups) with each element containing a matrix of (time x channel x subject) or (time x frequency x channel x subject) data. The function is called like this:
> 
> [stats, df, pvals] = statcondfieldtrip(data, 'paired', 'on', 'method', 'permutation', 'naccu', '1000', 'neighbours', neighbours, 'alpha', 0.05, 'structoutput', 'on');
> 
> The "neighbours" structure is created using the "ft_prepare_neighbours" function (template method) with no issues.
> 
> I'm not sure if this is a syntax error on my part or a missing input. Any assistance would be greatly appreciated!
> 
> Thank you,
> Taylor
> 
> Taylor Hearn
> Biomedical Engineering PhD Candidate
> APAcT-IGERT Fellow
> Arizona State University
> _______________________________________________
> 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



More information about the eeglablist mailing list