Insensitivity of Nadaraya–Watson estimators to design correlation Full article
| Journal |
Communications in Statistics - Theory and Methods
ISSN: 0361-0926 , E-ISSN: 1532-415X |
||||
|---|---|---|---|---|---|
| Output data | Year: 2022, Volume: 51, Number: 19, Pages: 6909-6918 Pages count : 10 DOI: 10.1080/03610926.2021.1876884 | ||||
| Tags | 62G08 | ||||
| Authors |
|
||||
| Affiliations |
|
Funding (2)
| 1 | Russian Foundation for Basic Research | 18-01-00074 |
| 2 | Sobolev Institute of Mathematics | 0314-2019-0008 |
Abstract:
We show that Nadaraya–Watson estimators in nonparametric regression may be uniformly consistent without any specification of the design correlation structure. In contrast to the predecessors’ results, the design is not required to be fixed or consisted of independentor weakly dependent random variables under various dependence conditions, and the design random observations are not necessarily identically distributed and nondegenerate. We suggest a new simple sufficient condition on the design which provides the uniform consistency of such estimators. Key words and phrases: nonparametric regression, Nadaraya–Watson estimators, uniform consistency, strongly dependent data.
Cite:
Linke Y.
, Borisov I.
Insensitivity of Nadaraya–Watson estimators to design correlation
Communications in Statistics - Theory and Methods. 2022. V.51. N19. P.6909-6918. DOI: 10.1080/03610926.2021.1876884 WOS Scopus РИНЦ OpenAlex
Insensitivity of Nadaraya–Watson estimators to design correlation
Communications in Statistics - Theory and Methods. 2022. V.51. N19. P.6909-6918. DOI: 10.1080/03610926.2021.1876884 WOS Scopus РИНЦ OpenAlex
Dates:
| Accepted: | Jan 11, 2021 |
| Published online: | Feb 1, 2021 |
Identifiers:
| Web of science: | WOS:000613783200001 |
| Scopus: | 2-s2.0-85100275617 |
| Elibrary: | 44962982 |
| OpenAlex: | W3128849502 |