文献类型：期刊文献

英文题名：Nearest neighbor estimates of regression

作者：Doksum, Kjell A.[1];Jiang, Jiancheng[2];Sun, Bo[3,4];Wang, Shuzhen[5]

第一作者：Doksum, Kjell A.

通讯作者：Jiang, JC[1]

机构：[1]Univ Wisconsin Madison, Madison, WI 53706 USA;[2]Univ N Carolina, Charlotte, NC 28223 USA;[3]Wuhan Univ, Wuhan 430072, Hubei, Peoples R China;[4]Jishou Univ, Jishou 416000, Hunan, Peoples R China;[5]Beijing Union Univ, Coll Business, Beijing 100101, Peoples R China

第一机构：Univ Wisconsin Madison, Madison, WI 53706 USA

通讯机构：[1]corresponding author), Univ N Carolina, Dept Math & Stat, Charlotte, NC 28223 USA.

年份：2017

卷号：110

起止页码：64-74

外文期刊名：COMPUTATIONAL STATISTICS & DATA ANALYSIS

收录：;EI(收录号：20170403286676);Scopus(收录号：2-s2.0-85010214337);WOS:【SCI-EXPANDED(收录号:WOS:000397370200005)】；

基金：This work was supported in part by the NSFC grant 71361010.

语种：英文

外文关键词：Empirical plug-in estimation; Local polynomial; Boundary adaptive; Minimax efficiency

摘要：New nearest neighbor estimators of the nonparametric regression function and its derivatives are developed. Asymptotic normality is obtained for the proposed estimators over the interior points and the boundary region. Connections with other estimators such as local polynomial smoothers are established. The proposed estimators are boundary adaptive and extensions of the Stute estimators. Asymptotic minimax risk properties are also established for the proposed estimators. Simulations are conducted to compare the performance of the proposed estimators with others. (C) 2017 Elsevier B.V. All rights reserved.