[Eeglablist] mixed model for EEG data

olaf.dimigen at hu-berlin.de olaf.dimigen at hu-berlin.de
Thu Jun 18 07:29:16 PDT 2015

Dear Lampros,


linear-mixed effects models (LME) have been used to analyze single-trial EEG responses in the field of psycholinguistics. Advantages include their suitability for handling unbalanced datasets (typical of EEG data with different numbers of bad trials per cell) and that there is no need to run separate F1/F2 ANOVAS (across participants and items). To my knowledge, the existing studies have usually computed separate LMMs for the data of each electrode (or electrode cluster) and for each consecutive time point (or time window, see Amsel, 2011 in particular), which creates some challenges with regard to multiple comparisons. See some refs below.


Best, Olaf


Amsel, B.D. (2011). Tracking real-time neural activation of conceptual knowledge using single-trial event-related potentials. Neuropsychologia, 49, 970-983
[computed LMMs for each electrode and running 10 ms time windows]


Dimigen, O., Sommer, W., Hohlfeld, A., Jacobs, A., & Kliegl, R. (2011). Coregistration of eye movements and EEG in natural reading: Analyses & Review. JEP:General, 140, 552-572. 
[included behavioral covariates as additional fixed effects]



Von: Lampros Perogamvros [mailto:lambros.pero at gmail.com] 
Gesendet: Dienstag, 16. Juni 2015 13:44
An: eeglablist at sccn.ucsd.edu
Betreff: [Eeglablist] mixed model for EEG data


Hi all,


We were just wondering whether you guys ever implemented a mixed model analysis for eeg data, and if so how you did it/setup the model? This model would be ideal when there are unequal numbers of observations per condition, and sometimes 0 observations for a condition for a given subject. This model would allow us to use all the data and do statistical tests on the individual observations rather than just averaging over all the observations for each subject, so it would be much more powerful. Are you aware of any such model for EEG?


Lampros Perogamvros MD

University of Wisconsin 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20150618/c265e5f1/attachment.html>

More information about the eeglablist mailing list