Instrumental variable estimation of heteroskedasticity adaptive error component models

Eduardo Fé

Research output: Contribution to journalArticle

Abstract

The linear panel data estimator proposed by Hausman and Taylor relaxes the hypothesis of exogenous regressors that is assumed by generalized least squares methods but, unlike the Fixed Effects estimator, it can handle endogenous time invariant explanatory variables in the regression equation. One of the assumptions underlying the estimator is the homoskedasticity of the error components. This can be restrictive in applications, and therefore in this paper the assumption is relaxed and more efficient adaptive versions of the estimator are presented.

LanguageEnglish
Pages577-615
Number of pages39
JournalStatistical Papers
Volume53
Issue number3
Early online date3 Feb 2011
DOIs
Publication statusPublished - Aug 2012

Fingerprint

Heteroskedasticity
Instrumental Variables
Error Model
Component Model
Estimator
Generalized Least Squares
Fixed Effects
Panel Data
Least Square Method
Regression
Invariant
Error component model
Instrumental variable estimation

Keywords

  • Hausman-Taylor
  • heteroskedasticity
  • local polynomial regression
  • panel data

Cite this

@article{b32c2170fa5d46d5ba9355e25cd10e16,
title = "Instrumental variable estimation of heteroskedasticity adaptive error component models",
abstract = "The linear panel data estimator proposed by Hausman and Taylor relaxes the hypothesis of exogenous regressors that is assumed by generalized least squares methods but, unlike the Fixed Effects estimator, it can handle endogenous time invariant explanatory variables in the regression equation. One of the assumptions underlying the estimator is the homoskedasticity of the error components. This can be restrictive in applications, and therefore in this paper the assumption is relaxed and more efficient adaptive versions of the estimator are presented.",
keywords = "Hausman-Taylor, heteroskedasticity, local polynomial regression, panel data",
author = "Eduardo F{\'e}",
year = "2012",
month = "8",
doi = "10.1007/s00362-011-0366-5",
language = "English",
volume = "53",
pages = "577--615",
journal = "Statistical Papers",
issn = "0932-5026",
number = "3",

}

Instrumental variable estimation of heteroskedasticity adaptive error component models. / Fé, Eduardo.

In: Statistical Papers, Vol. 53, No. 3, 08.2012, p. 577-615.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Instrumental variable estimation of heteroskedasticity adaptive error component models

AU - Fé, Eduardo

PY - 2012/8

Y1 - 2012/8

N2 - The linear panel data estimator proposed by Hausman and Taylor relaxes the hypothesis of exogenous regressors that is assumed by generalized least squares methods but, unlike the Fixed Effects estimator, it can handle endogenous time invariant explanatory variables in the regression equation. One of the assumptions underlying the estimator is the homoskedasticity of the error components. This can be restrictive in applications, and therefore in this paper the assumption is relaxed and more efficient adaptive versions of the estimator are presented.

AB - The linear panel data estimator proposed by Hausman and Taylor relaxes the hypothesis of exogenous regressors that is assumed by generalized least squares methods but, unlike the Fixed Effects estimator, it can handle endogenous time invariant explanatory variables in the regression equation. One of the assumptions underlying the estimator is the homoskedasticity of the error components. This can be restrictive in applications, and therefore in this paper the assumption is relaxed and more efficient adaptive versions of the estimator are presented.

KW - Hausman-Taylor

KW - heteroskedasticity

KW - local polynomial regression

KW - panel data

UR - http://www.scopus.com/inward/record.url?scp=84864371343&partnerID=8YFLogxK

U2 - 10.1007/s00362-011-0366-5

DO - 10.1007/s00362-011-0366-5

M3 - Article

VL - 53

SP - 577

EP - 615

JO - Statistical Papers

T2 - Statistical Papers

JF - Statistical Papers

SN - 0932-5026

IS - 3

ER -