Title and Abstract
Estimation of linear dynamic panel data models with time-invariant regressors
We propose a two-stage procedure to estimate the effects of time-invariant regressors in a dynamic Hausman-Taylor model. We first estimate the coefficients of the time-varying regressors and subsequently regress the first-stage residuals on the time-invariant regressors, providing analytical standard error adjustments. The two-stage approach benefits from increased robustness against model misspecification, allows exploiting advantages of estimators relying on transformations to eliminate the unit-specific heterogeneity, and can yield more efficient estimates for the coefficients of time-invariant regressors. The approach is illustrated with Monte Carlo simulations and the estimation of a dynamic gravity equation for U.S. outward foreign direct investment.
Kripfganz, S. and C. Schwarz (2015). Estimation of linear dynamic panel data models with time-invariant regressors.
ECB Working Paper 1838, European Central Bank.