Estimation methods in panel data models with observed and unobserved components : a Monte Carlo study

Recently some new techniques have been proposed for the estimation of the slope coefficients in presence of unobserved components. Though, the presence of common observed and unobserved factors is neither considered or the estimation of their impacts is not taken into account. In this work a range of estimators is surveyed and their finite-sample properties are examined by means of Monte Carlo experiments. We consider both the properties of estimators for the individual specific components and for the observed common effects. -- factor error structure ; principal component ; common regressors ; cross-section dependence ; large panels ; Monte Carlo simulations