Project

Bias correcting panel data estimators in dynamic models with cross-sectional dependence and endogeneity

Duration
01 October 2014 → 30 September 2018
Funding
Regional and community funding: Special Research Fund
Research disciplines
  • Natural sciences
    • Applied mathematics in specific fields
    • Statistics and numerical methods
  • Social sciences
    • Applied economics
    • Economic history
    • Macroeconomics and monetary economics
    • Microeconomics
    • Tourism
Keywords
bootstrap bias correction LSDV panel data dynamic models Fixed Effects (FE) estimator endogeneity Common Correlated Effects Pooled (CCEP) estimator cross-sectional dependence
 
Project description

The FE and CCEP estimators show considerable bias in dynamic models. Many corrections have been devised for FE, but none are applicable to case of endogenous regressors. We address this issue with the bootstrap method. The CCEP estimator is essential under cross-section dependence but has not yet been bias corrected. Such corrections (analytical and bootstrap-based) constitute our second research goal.