[FieldTrip] Variance estimates for connectivity measures

Schoffelen, J.M. (Jan Mathijs) jan.schoffelen at donders.ru.nl
Wed Nov 8 12:05:31 CET 2017

Dear Matthew,

I think it depends on the way that you compute these metrics. If you approach it parametrically (i.e. using MVAR-models) I think that the coefficients are computed across all observations by default. If you want a leave-one-out estimate of the coefficients, I think that you can use cfg.jackknife as an option to ft_mvaranalysis. How well this is supported throughout the rest of the analysis pipeline (i.e. ft_freqanalysis_mvar and ft_connectivityanalysis) I am not sure. I haven’t used this option for a long time, so the code may have become a bit rusty here and there.
If you are using a non-parametric approach (i.e. using ft_freqanalysis, followed by ft_connectivity_csd2transfer, which is called on the fly by ft_connectivityanalysis), I think there used to be some functionality to compute leave-one-outs on the fly, and then essentially treat them as ‘single trials’. Also there, I assume that the code has become a bit rusty, because it hasn’t been used for quite a while. Either way, I guess that an definitive answer to your question would require you to inspect the code in some more detail.

Best wishes,


J.M.Schoffelen, MD PhD
Senior Researcher, VIDI-fellow - PI, language in interaction
Telephone: +31-24-3614793
Physical location: room 00.028
Donders Centre for Cognitive Neuroimaging, Nijmegen, The Netherlands

On 20 Oct 2017, at 16:16, MATTHEW I BANKS <mibanks at wisc.edu<mailto:mibanks at wisc.edu>> wrote:

Greetings. Is it possible to use jackknife to get variance estimates for Granger, partial directed coherence and directed transfer function? I use it for wPLI, but cannot figure out how to do it for these other measures.

-Matt Banks

Matthew I. Banks, Ph.D.
Associate Professor
Department of Anesthesiology
University of Wisconsin
1300 University Avenue, Room 4605
Madison, WI 53706
office tel. (608)261-1143<tel:%28608%29261-1143>
lab tel. (608)263-6662<tel:%28608%29263-6662>
fax (608)263-2592<tel:%28608%29263-2592>
fieldtrip mailing list
fieldtrip at donders.ru.nl<mailto:fieldtrip at donders.ru.nl>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20171108/35630aef/attachment-0001.html>

More information about the fieldtrip mailing list