Penalized empirical likelihood estimation of semiparametric models

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

We propose an empirical likelihood-based estimation method for conditional estimating equations containing unknown functions, which can be applied for various semiparametric models. The proposed method is based on the methods of conditional empirical likelihood and penalization. Thus, our estimator is called the penalized empirical likelihood (PEL) estimator. For the whole parameter including infinite-dimensional unknown functions, we derive the consistency and a convergence rate of the PEL estimator. Furthermore, for the finite-dimensional parametric component, we show the asymptotic normality and efficiency of the PEL estimator. We illustrate the theory by three examples. Simulation results show reasonable finite sample properties of our estimator.

Original languageEnglish
Pages (from-to)1923-1954
Number of pages32
JournalJournal of Multivariate Analysis
Volume98
Issue number10
DOIs
Publication statusPublished - 2007 Nov 1
Externally publishedYes

Fingerprint

Penalized Likelihood
Empirical Likelihood
Semiparametric Model
Estimator
Conditional Likelihood
Unknown
Asymptotic Efficiency
Penalization
Estimating Equation
Asymptotic Normality
Rate of Convergence
Semiparametric model
Empirical likelihood
Likelihood estimation
Simulation

Keywords

  • Empirical likelihood
  • Penalization
  • Semiparametric model

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Numerical Analysis
  • Statistics and Probability

Cite this

Penalized empirical likelihood estimation of semiparametric models. / Otsu, Taisuke.

In: Journal of Multivariate Analysis, Vol. 98, No. 10, 01.11.2007, p. 1923-1954.

Research output: Contribution to journalArticle

@article{6ba2aef4c3d546eebcae1499c7d806a7,
title = "Penalized empirical likelihood estimation of semiparametric models",
abstract = "We propose an empirical likelihood-based estimation method for conditional estimating equations containing unknown functions, which can be applied for various semiparametric models. The proposed method is based on the methods of conditional empirical likelihood and penalization. Thus, our estimator is called the penalized empirical likelihood (PEL) estimator. For the whole parameter including infinite-dimensional unknown functions, we derive the consistency and a convergence rate of the PEL estimator. Furthermore, for the finite-dimensional parametric component, we show the asymptotic normality and efficiency of the PEL estimator. We illustrate the theory by three examples. Simulation results show reasonable finite sample properties of our estimator.",
keywords = "Empirical likelihood, Penalization, Semiparametric model",
author = "Taisuke Otsu",
year = "2007",
month = "11",
day = "1",
doi = "10.1016/j.jmva.2007.05.005",
language = "English",
volume = "98",
pages = "1923--1954",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",
number = "10",

}

TY - JOUR

T1 - Penalized empirical likelihood estimation of semiparametric models

AU - Otsu, Taisuke

PY - 2007/11/1

Y1 - 2007/11/1

N2 - We propose an empirical likelihood-based estimation method for conditional estimating equations containing unknown functions, which can be applied for various semiparametric models. The proposed method is based on the methods of conditional empirical likelihood and penalization. Thus, our estimator is called the penalized empirical likelihood (PEL) estimator. For the whole parameter including infinite-dimensional unknown functions, we derive the consistency and a convergence rate of the PEL estimator. Furthermore, for the finite-dimensional parametric component, we show the asymptotic normality and efficiency of the PEL estimator. We illustrate the theory by three examples. Simulation results show reasonable finite sample properties of our estimator.

AB - We propose an empirical likelihood-based estimation method for conditional estimating equations containing unknown functions, which can be applied for various semiparametric models. The proposed method is based on the methods of conditional empirical likelihood and penalization. Thus, our estimator is called the penalized empirical likelihood (PEL) estimator. For the whole parameter including infinite-dimensional unknown functions, we derive the consistency and a convergence rate of the PEL estimator. Furthermore, for the finite-dimensional parametric component, we show the asymptotic normality and efficiency of the PEL estimator. We illustrate the theory by three examples. Simulation results show reasonable finite sample properties of our estimator.

KW - Empirical likelihood

KW - Penalization

KW - Semiparametric model

UR - http://www.scopus.com/inward/record.url?scp=35348971441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35348971441&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2007.05.005

DO - 10.1016/j.jmva.2007.05.005

M3 - Article

AN - SCOPUS:35348971441

VL - 98

SP - 1923

EP - 1954

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

IS - 10

ER -