Estimation for single-index and partially linear single-index integrated models

Chaohua Dong, Jiti Gao, Dag Bjarne Tjostheim

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Estimation mainly for two classes of popular models, single-index and partially linear single-index models, is studied in this paper. Such models feature nonstationarity. Orthogonal series expansion is used to approximate the unknown integrable link functions in the models and a profile approach is used to derive the estimators. The findings include the dual rate of convergence of the estimators for the single-index models and a trio of convergence rates for the partially linear single-index models. A new central limit theorem is established for a plug-in estimator of the unknown link function. Meanwhile, a considerable extension to a class of partially nonlinear single-index models is discussed in Section 4. Monte Carlo simulation verifies these theoretical results. An empirical study furnishes an application of the proposed estimation procedures in practice.

Original languageEnglish
Pages (from-to)425-453
Number of pages29
JournalAnnals of Statistics
Volume44
Issue number1
DOIs
Publication statusPublished - 1 Feb 2016

Keywords

  • A trio of convergence rates
  • Dual convergence rates
  • Integrated time series
  • Orthogonal series expansion
  • Partially linear single-index models
  • Single-index models

Cite this

Dong, Chaohua ; Gao, Jiti ; Tjostheim, Dag Bjarne. / Estimation for single-index and partially linear single-index integrated models. In: Annals of Statistics. 2016 ; Vol. 44, No. 1. pp. 425-453.
@article{c778e4b8953548948c6c29df4fc66bd2,
title = "Estimation for single-index and partially linear single-index integrated models",
abstract = "Estimation mainly for two classes of popular models, single-index and partially linear single-index models, is studied in this paper. Such models feature nonstationarity. Orthogonal series expansion is used to approximate the unknown integrable link functions in the models and a profile approach is used to derive the estimators. The findings include the dual rate of convergence of the estimators for the single-index models and a trio of convergence rates for the partially linear single-index models. A new central limit theorem is established for a plug-in estimator of the unknown link function. Meanwhile, a considerable extension to a class of partially nonlinear single-index models is discussed in Section 4. Monte Carlo simulation verifies these theoretical results. An empirical study furnishes an application of the proposed estimation procedures in practice.",
keywords = "A trio of convergence rates, Dual convergence rates, Integrated time series, Orthogonal series expansion, Partially linear single-index models, Single-index models",
author = "Chaohua Dong and Jiti Gao and Tjostheim, {Dag Bjarne}",
year = "2016",
month = "2",
day = "1",
doi = "10.1214/15-AOS1372",
language = "English",
volume = "44",
pages = "425--453",
journal = "Annals of Statistics",
issn = "0090-5364",
publisher = "Institute of Mathematical Statistics",
number = "1",

}

Estimation for single-index and partially linear single-index integrated models. / Dong, Chaohua; Gao, Jiti; Tjostheim, Dag Bjarne.

In: Annals of Statistics, Vol. 44, No. 1, 01.02.2016, p. 425-453.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Estimation for single-index and partially linear single-index integrated models

AU - Dong, Chaohua

AU - Gao, Jiti

AU - Tjostheim, Dag Bjarne

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Estimation mainly for two classes of popular models, single-index and partially linear single-index models, is studied in this paper. Such models feature nonstationarity. Orthogonal series expansion is used to approximate the unknown integrable link functions in the models and a profile approach is used to derive the estimators. The findings include the dual rate of convergence of the estimators for the single-index models and a trio of convergence rates for the partially linear single-index models. A new central limit theorem is established for a plug-in estimator of the unknown link function. Meanwhile, a considerable extension to a class of partially nonlinear single-index models is discussed in Section 4. Monte Carlo simulation verifies these theoretical results. An empirical study furnishes an application of the proposed estimation procedures in practice.

AB - Estimation mainly for two classes of popular models, single-index and partially linear single-index models, is studied in this paper. Such models feature nonstationarity. Orthogonal series expansion is used to approximate the unknown integrable link functions in the models and a profile approach is used to derive the estimators. The findings include the dual rate of convergence of the estimators for the single-index models and a trio of convergence rates for the partially linear single-index models. A new central limit theorem is established for a plug-in estimator of the unknown link function. Meanwhile, a considerable extension to a class of partially nonlinear single-index models is discussed in Section 4. Monte Carlo simulation verifies these theoretical results. An empirical study furnishes an application of the proposed estimation procedures in practice.

KW - A trio of convergence rates

KW - Dual convergence rates

KW - Integrated time series

KW - Orthogonal series expansion

KW - Partially linear single-index models

KW - Single-index models

UR - http://www.scopus.com/inward/record.url?scp=85013223212&partnerID=8YFLogxK

U2 - 10.1214/15-AOS1372

DO - 10.1214/15-AOS1372

M3 - Article

VL - 44

SP - 425

EP - 453

JO - Annals of Statistics

JF - Annals of Statistics

SN - 0090-5364

IS - 1

ER -