The minimum weighted covariance determinant estimator for high-dimensional data

0546694 - ÚTIA 2023 RIV DE eng J - Článek v odborném periodiku
Kalina, Jan - Tichavský, J.
The minimum weighted covariance determinant estimator for high-dimensional data.
Advances in Data Analysis and Classification. Roč. 16, č. 4 (2022), s. 977-999. ISSN 1862-5347. E-ISSN 1862-5355
Grant CEP: GA ČR GA21-05325S; GA ČR(CZ) GA19-05704S
Institucionální podpora: RVO:67985556
Klíčová slova: High-dimensional data * Regularization * Robust estimation * Implicit weighting * Scatter matrix
Obor OECD: Pure mathematics
Impakt faktor: 1.6, rok: 2022
Způsob publikování: Omezený přístup
http://library.utia.cas.cz/separaty/2021/SI/kalina-0546694.pdf https://link.springer.com/article/10.1007/s11634-021-00471-6

In a variety of diverse applications, it is very desirable to perform a robust analysis of high-dimensional measurements without being harmed by the presence of a possibly larger percentage of outlying measurements. The minimum weighted covariance determinant (MWCD) estimator, based on implicit weights assigned to individual observations, represents a promising and flexible extension of the popular minimum covariance determinant (MCD) estimator of the expectation and scatter matrix of mlutivariate data. In this work, a regularized version of the MWCD denoted as the minimum regularized weighted covariance determinant (MRWCD) estimator is proposed. At the same time, it is accompanied by an outlier detection procedure. The novel MRWCD estimator is able to outperform other available robust estimators in several simulation scenarios, especially in estimating the scatter matrix of contaminated high-dimensional data.
Trvalý link: http://hdl.handle.net/11104/0323102