A1 Journal article (refereed)
On the usage of joint diagonalization in multivariate statistics (2022)

Nordhausen, K., & Ruiz-Gazen, A. (2022). On the usage of joint diagonalization in multivariate statistics. Journal of Multivariate Analysis, 188, Article 104844. https://doi.org/10.1016/j.jmva.2021.104844

JYU authors or editors

Publication details

All authors or editors: Nordhausen, Klaus; Ruiz-Gazen, Anne

Journal or series: Journal of Multivariate Analysis

ISSN: 0047-259X

eISSN: 1095-7243

Publication year: 2022

Volume: 188

Article number: 104844

Publisher: Elsevier

Publication country: United States

Publication language: English

DOI: https://doi.org/10.1016/j.jmva.2021.104844

Publication open access: Openly available

Publication channel open access: Partially open access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/79049

Abstract

Scatter matrices generalize the covariance matrix and are useful in many multivariate data analysis methods, including well-known principal component analysis (PCA), which is based on the diagonalization of the covariance matrix. The simultaneous diagonalization of two or more scatter matrices goes beyond PCA and is used more and more often. In this paper, we offer an overview of many methods that are based on a joint diagonalization. These methods range from the unsupervised context with invariant coordinate selection and blind source separation, which includes independent component analysis, to the supervised context with discriminant analysis and sliced inverse regression. They also encompass methods that handle dependent data such as time series or spatial data.

Keywords: mathematical statistics; multivariable methods; independent component analysis

Free keywords: Blind source separation; Dimension reduction; Invariant component selection; Scatter matrices; Supervised dimension reduction

Contributing organizations

Ministry reporting: Yes

VIRTA submission year: 2022

JUFO rating: 1