Empirical likelihood confidence regions in the single-index model with growing dimensions

Guangren Yang, Xia Cui, Sumin Hou

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper investigates statistical inference for the single-index model when the number of predictors grows with sample size. Empirical likelihood method for constructing confidence region for the index vector, which does not require a multivariate non parametric smoothing, is employed. However, the classical empirical likelihood ratio for this model does not remain valid because plug-in estimation of an infinite-dimensional nuisance parameter causes a non negligible bias and the diverging number of parameters/predictors makes the limit not chi-squared any more. To solve these problems, we define an empirical likelihood ratio based on newly proposed weighted estimating equations and show that it is asymptotically normal. Also we find that different weights used in the weighted residuals require, for asymptotic normality, different diverging rate of the number of predictors. However, the rate n1/3, which is a possible fastest rate when there are no any other conditions assumed in the setting under study, is still attainable. A simulation study is carried out to assess the performance of our method.

Original languageEnglish (US)
Pages (from-to)7562-7579
Number of pages18
JournalCommunications in Statistics - Theory and Methods
Volume46
Issue number15
DOIs
StatePublished - Aug 3 2017

Fingerprint

Single-index Model
Confidence Region
Empirical Likelihood
Predictors
Likelihood Ratio
Weighted Estimating Equations
Nonparametric Smoothing
Chi-squared
Likelihood Methods
Nuisance Parameter
Plug-in
Statistical Inference
Asymptotic Normality
Sample Size
Simulation Study
Valid
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

Cite this

@article{899ed1573e264e4ea35f9b7deb43e895,
title = "Empirical likelihood confidence regions in the single-index model with growing dimensions",
abstract = "This paper investigates statistical inference for the single-index model when the number of predictors grows with sample size. Empirical likelihood method for constructing confidence region for the index vector, which does not require a multivariate non parametric smoothing, is employed. However, the classical empirical likelihood ratio for this model does not remain valid because plug-in estimation of an infinite-dimensional nuisance parameter causes a non negligible bias and the diverging number of parameters/predictors makes the limit not chi-squared any more. To solve these problems, we define an empirical likelihood ratio based on newly proposed weighted estimating equations and show that it is asymptotically normal. Also we find that different weights used in the weighted residuals require, for asymptotic normality, different diverging rate of the number of predictors. However, the rate n1/3, which is a possible fastest rate when there are no any other conditions assumed in the setting under study, is still attainable. A simulation study is carried out to assess the performance of our method.",
author = "Guangren Yang and Xia Cui and Sumin Hou",
year = "2017",
month = "8",
day = "3",
doi = "10.1080/03610926.2016.1157190",
language = "English (US)",
volume = "46",
pages = "7562--7579",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "15",

}

Empirical likelihood confidence regions in the single-index model with growing dimensions. / Yang, Guangren; Cui, Xia; Hou, Sumin.

In: Communications in Statistics - Theory and Methods, Vol. 46, No. 15, 03.08.2017, p. 7562-7579.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Empirical likelihood confidence regions in the single-index model with growing dimensions

AU - Yang, Guangren

AU - Cui, Xia

AU - Hou, Sumin

PY - 2017/8/3

Y1 - 2017/8/3

N2 - This paper investigates statistical inference for the single-index model when the number of predictors grows with sample size. Empirical likelihood method for constructing confidence region for the index vector, which does not require a multivariate non parametric smoothing, is employed. However, the classical empirical likelihood ratio for this model does not remain valid because plug-in estimation of an infinite-dimensional nuisance parameter causes a non negligible bias and the diverging number of parameters/predictors makes the limit not chi-squared any more. To solve these problems, we define an empirical likelihood ratio based on newly proposed weighted estimating equations and show that it is asymptotically normal. Also we find that different weights used in the weighted residuals require, for asymptotic normality, different diverging rate of the number of predictors. However, the rate n1/3, which is a possible fastest rate when there are no any other conditions assumed in the setting under study, is still attainable. A simulation study is carried out to assess the performance of our method.

AB - This paper investigates statistical inference for the single-index model when the number of predictors grows with sample size. Empirical likelihood method for constructing confidence region for the index vector, which does not require a multivariate non parametric smoothing, is employed. However, the classical empirical likelihood ratio for this model does not remain valid because plug-in estimation of an infinite-dimensional nuisance parameter causes a non negligible bias and the diverging number of parameters/predictors makes the limit not chi-squared any more. To solve these problems, we define an empirical likelihood ratio based on newly proposed weighted estimating equations and show that it is asymptotically normal. Also we find that different weights used in the weighted residuals require, for asymptotic normality, different diverging rate of the number of predictors. However, the rate n1/3, which is a possible fastest rate when there are no any other conditions assumed in the setting under study, is still attainable. A simulation study is carried out to assess the performance of our method.

UR - http://www.scopus.com/inward/record.url?scp=85017510043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017510043&partnerID=8YFLogxK

U2 - 10.1080/03610926.2016.1157190

DO - 10.1080/03610926.2016.1157190

M3 - Article

AN - SCOPUS:85017510043

VL - 46

SP - 7562

EP - 7579

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 15

ER -