Number of the records: 1
Common Multivariate Estimators of Location and Scatter Capture the Symmetry of the Underlying Distribution
- 1.
SYSNO ASEP 0504387 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Common Multivariate Estimators of Location and Scatter Capture the Symmetry of the Underlying Distribution Author(s) Kalina, Jan (UIVT-O) RID, SAI, ORCID Source Title Communications in Statistics - Simulation and Computation. - : Taylor & Francis - ISSN 0361-0918
Roč. 50, č. 10 (2021), s. 2845-2857Number of pages 13 s. Language eng - English Country US - United States Keywords multivariate estimation ; symmetry test ; robust estimation ; scatter estimator ; axial symmetry Subject RIV BA - General Mathematics OECD category Statistics and probability Method of publishing Limited access Institutional support UIVT-O - RVO:67985807 UT WOS 000469602900001 EID SCOPUS 85066100659 DOI 10.1080/03610918.2019.1615624 Annotation The article discusses how various multivariate location and scatter estimators capture the symmetry of the underlying distribution. Very general sufficient conditions are formulated, which ensure various symmetry properties of functionals corresponding to location or scatter. Examples of robust multivariate estimators, which fulfill these conditions, are discussed in detail. The obtained symmetry of the estimators is applicable to hypothesis tests of symmetry of the underlying distribution of the multivariate data. For this task, we propose to perform permutation tests exploiting the nonparametric combination methodology. The performance of the newly proposed tests is illustrated on simulated as well as real data. The tests are suitable for small sample sizes and represent the first available symmetry tests suitable also for non-elliptical distributions and for more than just two variables. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2022 Electronic address http://dx.doi.org/10.1080/03610918.2019.1615624
Number of the records: 1