Bias corrections in testing and estimating semiparametric, single index models

Roger Klein, Chan Shen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Semiparametric methods are widely employed in applied work where the ability to conduct inferences is important. To establish asymptotic normality for making inferences, bias control mechanisms are often used in implementing semiparametric estimators. The first contribution of this paper is to propose a mechanism that enables us to establish asymptotic normality with regular kernels. In so doing, we argue that the resulting estimator performs very well in finite samples. Semiparametric models are commonly estimated under a single index assumption. Because the consistency of the estimator critically depends on this assumption being correct, our second objective is to develop a test for it. To ensure that the test statistic has good size and power properties in finite samples, we employ a bias control mechanism similar to that underlying the estimator. Furthermore, we structure the test so that its form adapts to the model under the alternative hypothesis. Monte Carlo results confirm that the bias control and the adaptive feature significantly improve the performance of the test statistic in finite samples.

Original languageEnglish (US)
Pages (from-to)1683-1718
Number of pages36
JournalEconometric Theory
Volume26
Issue number6
DOIs
StatePublished - Dec 1 2010

Fingerprint

normality
trend
statistics
Index model
Finite sample
Bias correction
Testing
Estimator
ability
performance
Control mechanism
Asymptotic normality
Test statistic
Inference
Semiparametric model
Kernel
Semiparametric methods
Semiparametric estimators

All Science Journal Classification (ASJC) codes

  • Social Sciences (miscellaneous)
  • Economics and Econometrics

Cite this

@article{f735a5e9db814f8689e0b954d40379ab,
title = "Bias corrections in testing and estimating semiparametric, single index models",
abstract = "Semiparametric methods are widely employed in applied work where the ability to conduct inferences is important. To establish asymptotic normality for making inferences, bias control mechanisms are often used in implementing semiparametric estimators. The first contribution of this paper is to propose a mechanism that enables us to establish asymptotic normality with regular kernels. In so doing, we argue that the resulting estimator performs very well in finite samples. Semiparametric models are commonly estimated under a single index assumption. Because the consistency of the estimator critically depends on this assumption being correct, our second objective is to develop a test for it. To ensure that the test statistic has good size and power properties in finite samples, we employ a bias control mechanism similar to that underlying the estimator. Furthermore, we structure the test so that its form adapts to the model under the alternative hypothesis. Monte Carlo results confirm that the bias control and the adaptive feature significantly improve the performance of the test statistic in finite samples.",
author = "Roger Klein and Chan Shen",
year = "2010",
month = "12",
day = "1",
doi = "10.1017/S0266466609990764",
language = "English (US)",
volume = "26",
pages = "1683--1718",
journal = "Econometric Theory",
issn = "0266-4666",
publisher = "Cambridge University Press",
number = "6",

}

Bias corrections in testing and estimating semiparametric, single index models. / Klein, Roger; Shen, Chan.

In: Econometric Theory, Vol. 26, No. 6, 01.12.2010, p. 1683-1718.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Bias corrections in testing and estimating semiparametric, single index models

AU - Klein, Roger

AU - Shen, Chan

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Semiparametric methods are widely employed in applied work where the ability to conduct inferences is important. To establish asymptotic normality for making inferences, bias control mechanisms are often used in implementing semiparametric estimators. The first contribution of this paper is to propose a mechanism that enables us to establish asymptotic normality with regular kernels. In so doing, we argue that the resulting estimator performs very well in finite samples. Semiparametric models are commonly estimated under a single index assumption. Because the consistency of the estimator critically depends on this assumption being correct, our second objective is to develop a test for it. To ensure that the test statistic has good size and power properties in finite samples, we employ a bias control mechanism similar to that underlying the estimator. Furthermore, we structure the test so that its form adapts to the model under the alternative hypothesis. Monte Carlo results confirm that the bias control and the adaptive feature significantly improve the performance of the test statistic in finite samples.

AB - Semiparametric methods are widely employed in applied work where the ability to conduct inferences is important. To establish asymptotic normality for making inferences, bias control mechanisms are often used in implementing semiparametric estimators. The first contribution of this paper is to propose a mechanism that enables us to establish asymptotic normality with regular kernels. In so doing, we argue that the resulting estimator performs very well in finite samples. Semiparametric models are commonly estimated under a single index assumption. Because the consistency of the estimator critically depends on this assumption being correct, our second objective is to develop a test for it. To ensure that the test statistic has good size and power properties in finite samples, we employ a bias control mechanism similar to that underlying the estimator. Furthermore, we structure the test so that its form adapts to the model under the alternative hypothesis. Monte Carlo results confirm that the bias control and the adaptive feature significantly improve the performance of the test statistic in finite samples.

UR - http://www.scopus.com/inward/record.url?scp=79251612960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79251612960&partnerID=8YFLogxK

U2 - 10.1017/S0266466609990764

DO - 10.1017/S0266466609990764

M3 - Article

AN - SCOPUS:79251612960

VL - 26

SP - 1683

EP - 1718

JO - Econometric Theory

JF - Econometric Theory

SN - 0266-4666

IS - 6

ER -