Strategies for addressing collinearity in multivariate linguistic data. (November 2018)

• Record Type: Journal Article
• Authors: Tomaschek, Fabian; Hendrix, Peter; Baayen, R. Harald
• Is Part Of: Journal of phonetics. Volume 71(2018)
• Page Start: 249
• Page End: 267
• Publication Date: 2018-11
• Subjects: Elastic net -- Supervised component generalized linear regression -- Random forests -- Collinearity -- Concurvity -- Segment duration; Phonetics -- Periodicals; Phonetics -- Periodicals; Phonétique -- Périodiques; Phonetics; Periodicals; Electronic journals; 414.05
• DOI: 10.1016/j.wocn.2018.09.004
• Languages: English
• ISSNs: 0095-4470

Abstract

Highlights: Regression results in suppression and enhancement when fitted to collinear data sets. Three methods to manage collinearity in data sets are presented. Jointly, they allow to understand the quantitative structure of empirical data. Abstract: When multiple correlated predictors are considered jointly in regression modeling, estimated coefficients may assume counterintuitive and theoretically uninterpretable values. We survey several statistical methods that implement strategies for the analysis of collinear data: regression with regularization (the elastic net), supervised component generalized linear regression, and random forests. Methods are illustrated for a data set with a wide range of predictors for segment duration in a German speech corpus. Results broadly converge, but each method has its own strengths and weaknesses. Jointly, they provide the analyst with somewhat different but complementary perspectives on the structure of collinear data.