Heavy tails of OLS

Thomas Valentin Mikosch; Casper de Vries

doi:10.1016/j.jeconom.2012.08.015

Heavy tails of OLS

Thomas Valentin Mikosch, Casper de Vries

Institut for Matematiske Fag

5 Citationer (Scopus)

Abstract

Suppose the tails of the noise distribution in a regression exhibit power law behavior. Then the
distribution of the OLS regression estimator inherits this tail behavior. This is relevant for regressions involving financial data. We derive explicit finite sample expressions for the tail probabilities of the distribution of the OLS estimator. These are useful for inference. Simulations for medium
sized samples reveal considerable deviations of the coefficient estimates from their true values, in line with our theoretical formulas. The formulas provide a benchmark for judging the observed highly variable cross country estimates of the expectations coefficient in yield curve regressions.

Originalsprog	Engelsk
Tidsskrift	Journal of Econometrics
Vol/bind	172
Udgave nummer	2
Sider (fra-til)	205-221
ISSN	0304-4076
DOI	https://doi.org/10.1016/j.jeconom.2012.08.015
Status	Udgivet - feb. 2013

Adgang til dokumentet

10.1016/j.jeconom.2012.08.015

Citationsformater

@article{54f8dc8321e446239c5b4f4bd4795d84,

title = "Heavy tails of OLS",

abstract = "Suppose the tails of the noise distribution in a regression exhibit power law behavior. Then thedistribution of the OLS regression estimator inherits this tail behavior. This is relevant for regressions involving financial data. We derive explicit finite sample expressions for the tail probabilities of the distribution of the OLS estimator. These are useful for inference. Simulations for mediumsized samples reveal considerable deviations of the coefficient estimates from their true values, in line with our theoretical formulas. The formulas provide a benchmark for judging the observed highly variable cross country estimates of the expectations coefficient in yield curve regressions. ",

author = "Mikosch, {Thomas Valentin} and {de Vries}, Casper",

year = "2013",

month = feb,

doi = "10.1016/j.jeconom.2012.08.015",

language = "English",

volume = "172",

pages = "205--221",

journal = "Journal of Econometrics",

issn = "0304-4076",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Heavy tails of OLS

AU - Mikosch, Thomas Valentin

AU - de Vries, Casper

PY - 2013/2

Y1 - 2013/2

N2 - Suppose the tails of the noise distribution in a regression exhibit power law behavior. Then thedistribution of the OLS regression estimator inherits this tail behavior. This is relevant for regressions involving financial data. We derive explicit finite sample expressions for the tail probabilities of the distribution of the OLS estimator. These are useful for inference. Simulations for mediumsized samples reveal considerable deviations of the coefficient estimates from their true values, in line with our theoretical formulas. The formulas provide a benchmark for judging the observed highly variable cross country estimates of the expectations coefficient in yield curve regressions.

AB - Suppose the tails of the noise distribution in a regression exhibit power law behavior. Then thedistribution of the OLS regression estimator inherits this tail behavior. This is relevant for regressions involving financial data. We derive explicit finite sample expressions for the tail probabilities of the distribution of the OLS estimator. These are useful for inference. Simulations for mediumsized samples reveal considerable deviations of the coefficient estimates from their true values, in line with our theoretical formulas. The formulas provide a benchmark for judging the observed highly variable cross country estimates of the expectations coefficient in yield curve regressions.

U2 - 10.1016/j.jeconom.2012.08.015

DO - 10.1016/j.jeconom.2012.08.015

M3 - Journal article

SN - 0304-4076

VL - 172

SP - 205

EP - 221

JO - Journal of Econometrics

JF - Journal of Econometrics

IS - 2

ER -