Bias-corrected quantile regression estimation of censored regression models

Research output: Contribution to journalArticleScientificpeer-review

Abstract

In this paper, an extension of the indirect inference methodology to semiparametric estimation is explored in the context of censored regression. Motivated by weak small-sample performance of the censored regression quantile estimator proposed by Powell (J Econom 32:143–155, 1986a), two- and three-step estimation methods were introduced for estimation of the censored regression model under conditional quantile restriction. While those stepwise estimators have been proven to be consistent and asymptotically normal, their finite sample performance greatly depends on the specification of an initial estimator that selects the subsample to be used in subsequent steps. In this paper, an alternative semiparametric estimator is introduced that does not involve a selection procedure in the first step. The proposed estimator is based on the indirect inference principle and is shown to be consistent and asymptotically normal under appropriate regularity conditions. Its performance is demonstrated and compared to existing methods by means of Monte Carlo simulations.
Original languageEnglish
Pages (from-to)215–247
Number of pages33
JournalStatistical Papers
Volume59
Early online date29 Mar 2016
DOIs
Publication statusPublished - 2018

Fingerprint

Censored Regression
Quantile Estimation
Regression Estimation
Quantile Regression
Regression Model
Estimator
Indirect Inference
Regression Quantiles
Conditional Quantiles
Semiparametric Estimation
Selection Procedures
Regularity Conditions
Small Sample
Monte Carlo Simulation
Censored regression model
Quantile regression
Specification
Restriction
Methodology
Alternatives

Keywords

  • asymptotic normality
  • censored regression
  • indirect inference
  • quantile regression

Cite this

@article{d7de3d0488cf4c53b068928665256a56,
title = "Bias-corrected quantile regression estimation of censored regression models",
abstract = "In this paper, an extension of the indirect inference methodology to semiparametric estimation is explored in the context of censored regression. Motivated by weak small-sample performance of the censored regression quantile estimator proposed by Powell (J Econom 32:143–155, 1986a), two- and three-step estimation methods were introduced for estimation of the censored regression model under conditional quantile restriction. While those stepwise estimators have been proven to be consistent and asymptotically normal, their finite sample performance greatly depends on the specification of an initial estimator that selects the subsample to be used in subsequent steps. In this paper, an alternative semiparametric estimator is introduced that does not involve a selection procedure in the first step. The proposed estimator is based on the indirect inference principle and is shown to be consistent and asymptotically normal under appropriate regularity conditions. Its performance is demonstrated and compared to existing methods by means of Monte Carlo simulations.",
keywords = "asymptotic normality, censored regression, indirect inference , quantile regression",
author = "Pavel Cizek and Serhan Sadikoglu",
year = "2018",
doi = "10.1007/s00362-016-0761-z",
language = "English",
volume = "59",
pages = "215–247",
journal = "Statistical Papers",
issn = "0932-5026",
publisher = "Springer New York",

}

Bias-corrected quantile regression estimation of censored regression models. / Cizek, Pavel; Sadikoglu, Serhan.

In: Statistical Papers, Vol. 59, 2018, p. 215–247.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Bias-corrected quantile regression estimation of censored regression models

AU - Cizek, Pavel

AU - Sadikoglu, Serhan

PY - 2018

Y1 - 2018

N2 - In this paper, an extension of the indirect inference methodology to semiparametric estimation is explored in the context of censored regression. Motivated by weak small-sample performance of the censored regression quantile estimator proposed by Powell (J Econom 32:143–155, 1986a), two- and three-step estimation methods were introduced for estimation of the censored regression model under conditional quantile restriction. While those stepwise estimators have been proven to be consistent and asymptotically normal, their finite sample performance greatly depends on the specification of an initial estimator that selects the subsample to be used in subsequent steps. In this paper, an alternative semiparametric estimator is introduced that does not involve a selection procedure in the first step. The proposed estimator is based on the indirect inference principle and is shown to be consistent and asymptotically normal under appropriate regularity conditions. Its performance is demonstrated and compared to existing methods by means of Monte Carlo simulations.

AB - In this paper, an extension of the indirect inference methodology to semiparametric estimation is explored in the context of censored regression. Motivated by weak small-sample performance of the censored regression quantile estimator proposed by Powell (J Econom 32:143–155, 1986a), two- and three-step estimation methods were introduced for estimation of the censored regression model under conditional quantile restriction. While those stepwise estimators have been proven to be consistent and asymptotically normal, their finite sample performance greatly depends on the specification of an initial estimator that selects the subsample to be used in subsequent steps. In this paper, an alternative semiparametric estimator is introduced that does not involve a selection procedure in the first step. The proposed estimator is based on the indirect inference principle and is shown to be consistent and asymptotically normal under appropriate regularity conditions. Its performance is demonstrated and compared to existing methods by means of Monte Carlo simulations.

KW - asymptotic normality

KW - censored regression

KW - indirect inference

KW - quantile regression

U2 - 10.1007/s00362-016-0761-z

DO - 10.1007/s00362-016-0761-z

M3 - Article

VL - 59

SP - 215

EP - 247

JO - Statistical Papers

JF - Statistical Papers

SN - 0932-5026

ER -