Simultaneous testing of the mean vector and covariance matrix among k populations for high-dimensional data

Masashi Hyodo and Takahiro Nishiyama

Communications in Statistics - Theory and Methods, 2021, vol. 50, issue 3, 663-684

Abstract: In this study, we propose an L2-norm-based test for simultaneous testing of the mean vector and covariance matrix for high-dimensional non-normal populations. We extend to k sample problems the procedures developed for two-sample problems by Hyodo and Nishiyama [Hyodo, M., Nishiyama, T., A simultaneous testing of the mean vector and the covariance matrix among two populations for high-dimensional data, TEST]. To accomplish this, we derive an asymptotic distribution of a test statistic based on differences of both mean vectors and covariance matrices. We also investigate the asymptotic sizes and powers of the proposed tests using this result. Finally, we study the finite sample and dimension performance of this test through Monte Carlo simulations.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2019.1639751 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:lstaxx:v:50:y:2021:i:3:p:663-684

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2019.1639751

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().