Empilrical likelihood for non-parametric regression models with missing responses: Multiple design case

被引：2

作者：

Lei, Qing-Zhu ^{[1
]}

Qin, Yong-Song ^{[1
]}

机构：

[1] Guangxi Normal Univ, Sch Math Sci, Guilin 541004, Guangxi, Peoples R China

来源：

ACTA MATHEMATICAE APPLICATAE SINICA-ENGLISH SERIES | 2011年 / 27卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Nonparametric regression; empirical likelihood; missing at random; confidence interval; EMPIRICAL LIKELIHOOD; LINEAR-MODELS; INFERENCE;

D O I：

10.1007/s10255-011-0035-4

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

Empirical likelihood (EL) ratio statistic on theta = g(x) is constructed based on the inverse probability weighted imputation approach in a nonparametric regression model Y = g(x)+E > (x a [0, 1] (p) ) with fixed designs and missing responses, which asymptotically has chi (1) (2) distribution. This result is used to obtain a EL based confidence interval on theta.

引用

页码：1 / 12

页数：12

共 17 条

[1]

C, 2000, BIOMETRIKA, V87, P946

[2] NONPARAMETRIC FUNCTION RECOVERING FROM NOISY OBSERVATIONS [J].

GEORGIEV, AA ;

GREBLICKI, W .

JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1986, 13 (01) :1-14

[3] CONSISTENT NONPARAMETRIC MULTIPLE-REGRESSION - THE FIXED DESIGN CASE [J].

GEORGIEV, AA .

JOURNAL OF MULTIVARIATE ANALYSIS, 1988, 25 (01) :100-110

[4]

GEORGIEV AA, 1989, STAT PROBABILITY LET, V7, P35

[5] METHODOLOGY AND ALGORITHMS OF EMPIRICAL LIKELIHOOD [J].

HALL, P ;

LASCALA, B .

INTERNATIONAL STATISTICAL REVIEW, 1990, 58 (02) :109-127

[6]

Hall P., 2013, BOOTSTRAP EDGEWORTH

[7]

LEI Q, 2008, CONFIDENCE INT UNPUB

[8] Estimation in partially linear models with missing covariates [J].

Liang, H ;

Wang, SJ ;

Robins, JM ;

Carroll, RJ .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2004, 99 (466) :357-367

[9]

Little R. J. A., 1987, STAT ANAL MISSING DA

[10] EMPIRICAL LIKELIHOOD RATIO CONFIDENCE-REGIONS [J].

OWEN, A .

ANNALS OF STATISTICS, 1990, 18 (01) :90-120

← 1 2 →