Insensitivity of Nadaraya–Watson estimators to design correlation. Issue 19 (2nd October 2022)

• Record Type: Journal Article
• Authors: Linke, Yuliana; Borisov, Igor
• Is Part Of: Communications in statistics. Volume 51:Issue 19(2022)
• Page Start: 6909
• Page End: 6918
• Publication Date: 2022-10-02
• Subjects: 62G08; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2021.1876884
• Languages: English
• ISSNs: 0361-0926

Abstract

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 independent or 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.