Tail dependence of OLS

Jochem Oorschot; Chen Zhou

doi:10.1017/S0266466621000311

Tail dependence of OLS

Jochem Oorschot, Chen Zhou

Econometrics

Research output: Contribution to journal › Article › Academic

Abstract

This paper shows that if the errors in a multiple regression model are heavy-tailed, the ordinary least squares (OLS) estimators for the regression coefficients are tail-dependent. The tail dependence arises, because the OLS estimators are stochastic linear combinations of heavy-tailed random variables. Moreover, tail dependence also exists between the fitted sum of squares (FSS) and the residual sum of squares (RSS), because they are stochastic quadratic combinations of heavy-tailed random variables.

Original language	English
Journal	Econometric Theory
Volume	accepted
DOIs	https://doi.org/10.1017/S0266466621000311
Publication status	Published - 2 Jul 2021

Bibliographical note

Publisher Copyright:
© The Author(s), 2021. Published by Cambridge University Press.

Access to Document

10.1017/S0266466621000311

http://hdl.handle.net/1765/134641

Cite this

@article{5e6e1ecf14e1457693f140616dc01cd1,

title = "Tail dependence of OLS",

abstract = "This paper shows that if the errors in a multiple regression model are heavy-tailed, the ordinary least squares (OLS) estimators for the regression coefficients are tail-dependent. The tail dependence arises, because the OLS estimators are stochastic linear combinations of heavy-tailed random variables. Moreover, tail dependence also exists between the fitted sum of squares (FSS) and the residual sum of squares (RSS), because they are stochastic quadratic combinations of heavy-tailed random variables.",

author = "Jochem Oorschot and Chen Zhou",

note = "Publisher Copyright: {\textcopyright} The Author(s), 2021. Published by Cambridge University Press.",

year = "2021",

month = jul,

day = "2",

doi = "10.1017/S0266466621000311",

language = "English",

volume = "accepted",

journal = "Econometric Theory",

issn = "0266-4666",

publisher = "Cambridge University Press",

}

TY - JOUR

T1 - Tail dependence of OLS

AU - Oorschot, Jochem

AU - Zhou, Chen

PY - 2021/7/2

Y1 - 2021/7/2

N2 - This paper shows that if the errors in a multiple regression model are heavy-tailed, the ordinary least squares (OLS) estimators for the regression coefficients are tail-dependent. The tail dependence arises, because the OLS estimators are stochastic linear combinations of heavy-tailed random variables. Moreover, tail dependence also exists between the fitted sum of squares (FSS) and the residual sum of squares (RSS), because they are stochastic quadratic combinations of heavy-tailed random variables.

AB - This paper shows that if the errors in a multiple regression model are heavy-tailed, the ordinary least squares (OLS) estimators for the regression coefficients are tail-dependent. The tail dependence arises, because the OLS estimators are stochastic linear combinations of heavy-tailed random variables. Moreover, tail dependence also exists between the fitted sum of squares (FSS) and the residual sum of squares (RSS), because they are stochastic quadratic combinations of heavy-tailed random variables.

UR - http://www.scopus.com/inward/record.url?scp=85109384340&partnerID=8YFLogxK

U2 - 10.1017/S0266466621000311

DO - 10.1017/S0266466621000311

M3 - Article

VL - accepted

JO - Econometric Theory

JF - Econometric Theory

SN - 0266-4666

ER -

Tail dependence of OLS

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this