Dynamic linear panel regression models with interactive fixed effects

Hyungsik Roger Moon, Martin Weidner

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

We analyze linear panel regression models with interactive fixed effects and predetermined regressors, for example lagged-dependent variables. The first-order asymptotic theory of the least squares (LS) estimator of the regression coefficients is worked out in the limit where both the cross-sectional dimension and the number of time periods become large. We find two sources of asymptotic bias of the LS estimator: bias due to correlation or heteroscedasticity of the idiosyncratic error term, and bias due to predetermined (as opposed to strictly exogenous) regressors. We provide a bias-corrected LS estimator. We also present bias-corrected versions of the three classical test statistics (Wald, LR, and LM test) and show their asymptotic distribution is a χ2-distribution. Monte Carlo simulations show the bias correction of the LS estimator and of the test statistics also work well for finite sample sizes.

Original languageEnglish
Pages (from-to)158-195
Number of pages38
JournalEconometric Theory
Volume33
Issue number1
DOIs
Publication statusPublished - 2017 Feb 1

Fingerprint

regression
trend
statistics
Panel regression
Least squares estimator
Regression model
Fixed effects
simulation
Test statistic
Asymptotic bias
Finite sample
Asymptotic theory
Heteroscedasticity
Asymptotic distribution
LM test
Monte Carlo simulation
Sample size
Present bias
Coefficients
Bias correction

All Science Journal Classification (ASJC) codes

  • Social Sciences (miscellaneous)
  • Economics and Econometrics

Cite this

@article{b800e04e573445e2b08957c8977e31e6,
title = "Dynamic linear panel regression models with interactive fixed effects",
abstract = "We analyze linear panel regression models with interactive fixed effects and predetermined regressors, for example lagged-dependent variables. The first-order asymptotic theory of the least squares (LS) estimator of the regression coefficients is worked out in the limit where both the cross-sectional dimension and the number of time periods become large. We find two sources of asymptotic bias of the LS estimator: bias due to correlation or heteroscedasticity of the idiosyncratic error term, and bias due to predetermined (as opposed to strictly exogenous) regressors. We provide a bias-corrected LS estimator. We also present bias-corrected versions of the three classical test statistics (Wald, LR, and LM test) and show their asymptotic distribution is a χ2-distribution. Monte Carlo simulations show the bias correction of the LS estimator and of the test statistics also work well for finite sample sizes.",
author = "Moon, {Hyungsik Roger} and Martin Weidner",
year = "2017",
month = "2",
day = "1",
doi = "10.1017/S0266466615000328",
language = "English",
volume = "33",
pages = "158--195",
journal = "Econometric Theory",
issn = "0266-4666",
publisher = "Cambridge University Press",
number = "1",

}

Dynamic linear panel regression models with interactive fixed effects. / Moon, Hyungsik Roger; Weidner, Martin.

In: Econometric Theory, Vol. 33, No. 1, 01.02.2017, p. 158-195.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Dynamic linear panel regression models with interactive fixed effects

AU - Moon, Hyungsik Roger

AU - Weidner, Martin

PY - 2017/2/1

Y1 - 2017/2/1

N2 - We analyze linear panel regression models with interactive fixed effects and predetermined regressors, for example lagged-dependent variables. The first-order asymptotic theory of the least squares (LS) estimator of the regression coefficients is worked out in the limit where both the cross-sectional dimension and the number of time periods become large. We find two sources of asymptotic bias of the LS estimator: bias due to correlation or heteroscedasticity of the idiosyncratic error term, and bias due to predetermined (as opposed to strictly exogenous) regressors. We provide a bias-corrected LS estimator. We also present bias-corrected versions of the three classical test statistics (Wald, LR, and LM test) and show their asymptotic distribution is a χ2-distribution. Monte Carlo simulations show the bias correction of the LS estimator and of the test statistics also work well for finite sample sizes.

AB - We analyze linear panel regression models with interactive fixed effects and predetermined regressors, for example lagged-dependent variables. The first-order asymptotic theory of the least squares (LS) estimator of the regression coefficients is worked out in the limit where both the cross-sectional dimension and the number of time periods become large. We find two sources of asymptotic bias of the LS estimator: bias due to correlation or heteroscedasticity of the idiosyncratic error term, and bias due to predetermined (as opposed to strictly exogenous) regressors. We provide a bias-corrected LS estimator. We also present bias-corrected versions of the three classical test statistics (Wald, LR, and LM test) and show their asymptotic distribution is a χ2-distribution. Monte Carlo simulations show the bias correction of the LS estimator and of the test statistics also work well for finite sample sizes.

UR - http://www.scopus.com/inward/record.url?scp=84950294768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84950294768&partnerID=8YFLogxK

U2 - 10.1017/S0266466615000328

DO - 10.1017/S0266466615000328

M3 - Article

AN - SCOPUS:84950294768

VL - 33

SP - 158

EP - 195

JO - Econometric Theory

JF - Econometric Theory

SN - 0266-4666

IS - 1

ER -