Skip to main navigation Skip to search Skip to main content

Asymptotic properties for estimates of nonparametric regression models based on negatively associated sequences

  • Han Ying Liang*
  • , Bing Yi Jing*
  • *Corresponding author for this work

Research output: Contribution to journalJournal Articlepeer-review

Abstract

Consider the nonparametric regression model Yni = g (xni) + εni for i = 1,..., n, where g is unknown, xni are fixed design points, and εni are negatively associated random errors. Nonparametric estimator gn (x) of g(x) will be introduced and its asymptotic properties are studied. In particular, the pointwise and uniform convergence of gn (x) and its asymptotic normality will be investigated. This extends the earlier work on independent random errors (e.g. see J. Multivariate Anal. 25(1) (1988) 100).

Original languageEnglish
Pages (from-to)227-245
Number of pages19
JournalJournal of Multivariate Analysis
Volume95
Issue number2
Early online date10 Dec 2004
DOIs
Publication statusPublished - Aug 2005

Keywords

  • Nonparametric regression
  • Negatively associated random error
  • Consistency
  • Complete convergence
  • Asymptotic normality

Fingerprint

Dive into the research topics of 'Asymptotic properties for estimates of nonparametric regression models based on negatively associated sequences'. Together they form a unique fingerprint.

Cite this