Nonparametric Estimation of Conditional Quantile Functions in the Presence of Irrelevant Covariates

Xirong Chen; Degui Li; Qi Li; Zheng Li

doi:10.1016/j.jeconom.2019.04.037

Nonparametric Estimation of Conditional Quantile Functions in the Presence of Irrelevant Covariates

Xirong Chen, Degui Li, Qi Li, Zheng Li

Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

Allowing for the existence of irrelevant covariates, we study the problem of estimating
a conditional quantile function nonparametrically with mixed discrete and continuous data. We estimate the conditional quantile regression function using the check-function-based kernel method and suggest a data-driven cross-validation (CV) approach to simultaneously determine the optimal smoothing parameters and remove the irrelevant covariates. When the number of covariates is large, we first use a screening method to remove the irrelevant covariates and then apply the CV criterion to those that survive the screening procedure. Simulations and an empirical application demonstrate the usefulness of the proposed methods.

Original language	English
Pages (from-to)	433-450
Number of pages	18
Journal	Journal of Econometrics
Volume	212
Issue number	2
Early online date	22 May 2019
DOIs	https://doi.org/10.1016/j.jeconom.2019.04.037
Publication status	Published - Oct 2019

Access to Document

10.1016/j.jeconom.2019.04.037

CLLL-2018166-0128-full-30-April-2019
© Elsevier, 2019. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy.
Accepted author manuscript, 399 KBLicence: CC BY-NC-ND

Cite this

@article{7116c4d4b4aa484b8ddcdca997459f41,

title = "Nonparametric Estimation of Conditional Quantile Functions in the Presence of Irrelevant Covariates",

abstract = "Allowing for the existence of irrelevant covariates, we study the problem of estimatinga conditional quantile function nonparametrically with mixed discrete and continuous data. We estimate the conditional quantile regression function using the check-function-based kernel method and suggest a data-driven cross-validation (CV) approach to simultaneously determine the optimal smoothing parameters and remove the irrelevant covariates. When the number of covariates is large, we first use a screening method to remove the irrelevant covariates and then apply the CV criterion to those that survive the screening procedure. Simulations and an empirical application demonstrate the usefulness of the proposed methods.",

author = "Xirong Chen and Degui Li and Qi Li and Zheng Li",

year = "2019",

month = oct,

doi = "10.1016/j.jeconom.2019.04.037",

language = "English",

volume = "212",

pages = "433--450",

journal = "Journal of Econometrics",

issn = "0304-4076",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Nonparametric Estimation of Conditional Quantile Functions in the Presence of Irrelevant Covariates

AU - Chen, Xirong

AU - Li, Degui

AU - Li, Qi

AU - Li, Zheng

PY - 2019/10

Y1 - 2019/10

N2 - Allowing for the existence of irrelevant covariates, we study the problem of estimatinga conditional quantile function nonparametrically with mixed discrete and continuous data. We estimate the conditional quantile regression function using the check-function-based kernel method and suggest a data-driven cross-validation (CV) approach to simultaneously determine the optimal smoothing parameters and remove the irrelevant covariates. When the number of covariates is large, we first use a screening method to remove the irrelevant covariates and then apply the CV criterion to those that survive the screening procedure. Simulations and an empirical application demonstrate the usefulness of the proposed methods.

AB - Allowing for the existence of irrelevant covariates, we study the problem of estimatinga conditional quantile function nonparametrically with mixed discrete and continuous data. We estimate the conditional quantile regression function using the check-function-based kernel method and suggest a data-driven cross-validation (CV) approach to simultaneously determine the optimal smoothing parameters and remove the irrelevant covariates. When the number of covariates is large, we first use a screening method to remove the irrelevant covariates and then apply the CV criterion to those that survive the screening procedure. Simulations and an empirical application demonstrate the usefulness of the proposed methods.

U2 - 10.1016/j.jeconom.2019.04.037

DO - 10.1016/j.jeconom.2019.04.037

M3 - Article

VL - 212

SP - 433

EP - 450

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -