Bootstrap-based corrections for LS and IV estimators in dynamic panels (01D30408)
The LSDV estimator is known to be strongly biased in dynamic panels. The goal of this project is to investigate the performance of a boostrap-based bias correction for models with higher order dynamics and a vector of (endogenous) explanatory variables. Furthermore, we explore alternative ways to estimate the long-term impact. Finally, we want to apply our findings to the convergence debate.