1] Generalized additive modeling on ERP data
In our paper on age effects in second-language processing, we used generalized additive mixed-effects regression modelling (GAM) to analyze the ERP signal. You can view the R code that was used to run the models here. The latter script additionally contains a logistic mixed-effects regression analysis of some behavioral data (end-of-sentence grammaticality judgments) and an ANOVA and correlational analysis of the ERP data as a comparison to the GAM analysis.
2] EEG data formatting before applying (generalized additive) mixed models
I sometimes receive questions from colleagues and students about how they can export their un-averaged EEG data and convert it into the appropriate format before applying (generalized additive) mixed-effects models. This example R script shows you how I prepare my ERP data, after exporting from Brain Vision Analyzer 2 (instructions for exporting are inside the script). It includes steps for combining the ERP data with the output from stimulus presentation software, in my case E-Prime 2. If you want to run the script step by step to see what it does, you can use this example from my data set.
A recommended course on mixed-effects regression and generalized additive modeling in linguistics, taught by Martijn Wieling.