IV estimation of panels with factor residuals

Donald Robertson, Vasileios Sarafidis

Research output: Contribution to journalArticleResearchpeer-review

Abstract

This paper proposes a new instrumental variables approach for consistent and asymptotically efficient estimation of panel data models with weakly exogenous or endogenous regressors and residuals generated by a multi-factor error structure. In this case, the standard dynamic panel estimators fail to provide consistent estimates of the parameters. The novelty of our approach is that we introduce new parameters to represent the unobserved covariances between the instruments and the factor component of the residual; these parameters are estimable when N is large. Some important estimation and identification issues are studied in detail. The finite sample performance of the proposed estimators is investigated using simulated data. The results show that the method produces reliable estimates of the parameters over several parameterisations.
Original languageEnglish
Pages (from-to)526 - 541
Number of pages16
JournalJournal of Econometrics
Volume185
Issue number2
DOIs
Publication statusPublished - 2015

Cite this

Robertson, Donald ; Sarafidis, Vasileios. / IV estimation of panels with factor residuals. In: Journal of Econometrics. 2015 ; Vol. 185, No. 2. pp. 526 - 541.
@article{5b70239d3456466baa3fb0365abe715e,
title = "IV estimation of panels with factor residuals",
abstract = "This paper proposes a new instrumental variables approach for consistent and asymptotically efficient estimation of panel data models with weakly exogenous or endogenous regressors and residuals generated by a multi-factor error structure. In this case, the standard dynamic panel estimators fail to provide consistent estimates of the parameters. The novelty of our approach is that we introduce new parameters to represent the unobserved covariances between the instruments and the factor component of the residual; these parameters are estimable when N is large. Some important estimation and identification issues are studied in detail. The finite sample performance of the proposed estimators is investigated using simulated data. The results show that the method produces reliable estimates of the parameters over several parameterisations.",
author = "Donald Robertson and Vasileios Sarafidis",
year = "2015",
doi = "10.1016/j.jeconom.2014.12.001",
language = "English",
volume = "185",
pages = "526 -- 541",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier",
number = "2",

}

IV estimation of panels with factor residuals. / Robertson, Donald; Sarafidis, Vasileios.

In: Journal of Econometrics, Vol. 185, No. 2, 2015, p. 526 - 541.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - IV estimation of panels with factor residuals

AU - Robertson, Donald

AU - Sarafidis, Vasileios

PY - 2015

Y1 - 2015

N2 - This paper proposes a new instrumental variables approach for consistent and asymptotically efficient estimation of panel data models with weakly exogenous or endogenous regressors and residuals generated by a multi-factor error structure. In this case, the standard dynamic panel estimators fail to provide consistent estimates of the parameters. The novelty of our approach is that we introduce new parameters to represent the unobserved covariances between the instruments and the factor component of the residual; these parameters are estimable when N is large. Some important estimation and identification issues are studied in detail. The finite sample performance of the proposed estimators is investigated using simulated data. The results show that the method produces reliable estimates of the parameters over several parameterisations.

AB - This paper proposes a new instrumental variables approach for consistent and asymptotically efficient estimation of panel data models with weakly exogenous or endogenous regressors and residuals generated by a multi-factor error structure. In this case, the standard dynamic panel estimators fail to provide consistent estimates of the parameters. The novelty of our approach is that we introduce new parameters to represent the unobserved covariances between the instruments and the factor component of the residual; these parameters are estimable when N is large. Some important estimation and identification issues are studied in detail. The finite sample performance of the proposed estimators is investigated using simulated data. The results show that the method produces reliable estimates of the parameters over several parameterisations.

U2 - 10.1016/j.jeconom.2014.12.001

DO - 10.1016/j.jeconom.2014.12.001

M3 - Article

VL - 185

SP - 526

EP - 541

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -