Local Composite Quantile Regression Smoothing: Flexible Data Structure and Cross-Validation

20 Pages Posted: 8 May 2018 Last revised: 10 Mar 2019

See all articles by Xiao Huang

Xiao Huang

Kennesaw State University

Zhongjian Lin

University of Georgia

Date Written: March 7, 2019

Abstract

In this paper, we study the local composite quantile regression estimator for mixed categorical and continuous data. The local composite quantile estimator is an efficient and safe alternative to the local polynomial method and has been well-studied for continuous covariates. Generalization of the local composite quantile regression estimator to a flexible data structure is appealing to practitioners as empirical studies often encounter categorical data. Furthermore, we study the theoretical properties of the cross-validated bandwidth selection for the local composite quantile estimator. Under mild conditions, we derive the rates of convergence of the cross-validated smoothing parameters to their optimal benchmark values for both categorical and continuous covariates. Monte Carlo experiments show that the proposed estimator may have large efficiency gains compared to the local linear estimator. Furthermore, we illustrate the robustness of the local composite quantile estimator using the Boston housing dataset.

Keywords: Local Composite Quantile Regression, Mixed Categorical and Continuous Data, Cross-Validation, Efficiency

JEL Classification: C14, C21

Suggested Citation

Huang, Xiao and Lin, Zhongjian, Local Composite Quantile Regression Smoothing: Flexible Data Structure and Cross-Validation (March 7, 2019). Available at SSRN: https://ssrn.com/abstract=3167411 or http://dx.doi.org/10.2139/ssrn.3167411

Xiao Huang (Contact Author)

Kennesaw State University ( email )

560 Parliament Garden Way
Kennesaw, GA 30144
United States
(470) 578-6318 (Phone)
(470) 578-9022 (Fax)

Zhongjian Lin

University of Georgia ( email )

620 S. Lumpkin St.
Athens, GA 30602
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
68
Abstract Views
510
Rank
603,475
PlumX Metrics