ℓ1-penalized linear mixed-effects models for high dimensional data with application to BCI

► We apply a novel mixed-effects model to high dimensional BCI data for the first time. ► The model inherently compensates shifts in the input space. ► We can now distinguish within- and between-subject variability. ► The model leads to a more compact and superior BCI subject-independent classifier. ► The framework is applicable to a wide range of experiments in many domains.