A robust test of exogeneity based on quantile regressions

Tae-Hwan Kim, Christophe Muller

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a robust test of exogeneity. The test statistics is constructed from quantile regression estimators, which are robust to heavy tails of errors. We derive the asymptotic distribution of the test statistic under the null hypothesis of exogeneity at a given quantile. The finite sample properties of the test are investigated through Monte Carlo simulations that exhibit not only good size and power properties, but also good robustness to outliers.

Original languageEnglish
Pages (from-to)2161-2174
Number of pages14
JournalJournal of Statistical Computation and Simulation
Volume87
Issue number11
DOIs
Publication statusPublished - 2017 Jul 24

Fingerprint

Robust Tests
Quantile Regression
Test Statistic
Statistics
Heavy Tails
Regression Estimator
Quantile
Null hypothesis
Asymptotic distribution
Outlier
Monte Carlo Simulation
Robustness
Exogeneity
Test statistic
Quantile regression
Estimator
Outliers
Monte Carlo simulation
Heavy tails
Finite sample properties

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

@article{2ef3649a0f144fd0b04887dde0f3176b,
title = "A robust test of exogeneity based on quantile regressions",
abstract = "In this paper, we propose a robust test of exogeneity. The test statistics is constructed from quantile regression estimators, which are robust to heavy tails of errors. We derive the asymptotic distribution of the test statistic under the null hypothesis of exogeneity at a given quantile. The finite sample properties of the test are investigated through Monte Carlo simulations that exhibit not only good size and power properties, but also good robustness to outliers.",
author = "Tae-Hwan Kim and Christophe Muller",
year = "2017",
month = "7",
day = "24",
doi = "10.1080/00949655.2017.1319947",
language = "English",
volume = "87",
pages = "2161--2174",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "11",

}

A robust test of exogeneity based on quantile regressions. / Kim, Tae-Hwan; Muller, Christophe.

In: Journal of Statistical Computation and Simulation, Vol. 87, No. 11, 24.07.2017, p. 2161-2174.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A robust test of exogeneity based on quantile regressions

AU - Kim, Tae-Hwan

AU - Muller, Christophe

PY - 2017/7/24

Y1 - 2017/7/24

N2 - In this paper, we propose a robust test of exogeneity. The test statistics is constructed from quantile regression estimators, which are robust to heavy tails of errors. We derive the asymptotic distribution of the test statistic under the null hypothesis of exogeneity at a given quantile. The finite sample properties of the test are investigated through Monte Carlo simulations that exhibit not only good size and power properties, but also good robustness to outliers.

AB - In this paper, we propose a robust test of exogeneity. The test statistics is constructed from quantile regression estimators, which are robust to heavy tails of errors. We derive the asymptotic distribution of the test statistic under the null hypothesis of exogeneity at a given quantile. The finite sample properties of the test are investigated through Monte Carlo simulations that exhibit not only good size and power properties, but also good robustness to outliers.

UR - http://www.scopus.com/inward/record.url?scp=85018343496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018343496&partnerID=8YFLogxK

U2 - 10.1080/00949655.2017.1319947

DO - 10.1080/00949655.2017.1319947

M3 - Article

VL - 87

SP - 2161

EP - 2174

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 11

ER -