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

• Published in: NeuroImage (Orlando, Fla.) Vol. 56; no. 4; pp. 2100 - 2108
• Main Authors: Fazli, Siamac, Danóczy, Márton, Schelldorfer, Jürg, Müller, Klaus-Robert
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 15.06.2011
• Subjects: BCI; Mixed-effects model; Sparsity; Subject-independent; Mixed-effects model; BCI; Sparsity; Subject-independent
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2011.03.061

Recently, a novel statistical model has been proposed to estimate population effects and individual variability between subgroups simultaneously, by extending Lasso methods. We will for the first time apply this so-called ℓ1-penalized linear regression mixed-effects model for a large scale real world problem: we study a large set of brain computer interface data and through the novel estimator are able to obtain a subject-independent classifier that compares favorably with prior zero-training algorithms. This unifying model inherently compensates shifts in the input space attributed to the individuality of a subject. In particular we are now for the first time able to differentiate within-subject and between-subject variability. Thus a deeper understanding both of the underlying statistical and physiological structures of the data is gained. ► 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.