Group level analysis on individual differences

✉️ Mailing List Archive (read-only)
1

External Email - Use Caution

Dear MNE team,

I've scrolled through the documentation on MNE and also searched the mailing list but could not really find any documentation on how to conduct group level analysis investigating individual differences. I would like to explore whether the difference in ERPS between two conditions within subjects differs along a behavioral variable across individuals. Is this feasible with the functions provided in MNE?
Ideally I would like to know at each timepoint how the difference between conditions correlates with the individual difference measure.

Thank you very much for your help,

Sebastian
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20200610/06d4a6fc/attachment.html

2

External Email - Use Caution

For individual differences, you'll definitely want to use mixed-effects
models. Unfortunately, the options for mixed models is rather limited in
Python in general.

That said, I've used MNE for years to do all the EEG/ERP wrangling and
then used lme4/MixedModels.jl for the analysis of the extracted samples.
For example, check out (shameless self promotion!): https://osf.io/pnaku

Phillip

3

External Email - Use Caution

To facilitate interfacing with R there is https://mne-tools.github.io/mne-r/index.html
For toy examples, see vignettes, for example: https://mne.tools/mne-r/articles/plot_evoked_multilevel_model.html
Hope that helps,
Denis