Two-step estimation of panel data models with censored endogenous variables and selection bias

摘要: This paper presents some two-step estimators for a wide range of parametric panel data models with censored endogenous variables and sample selection bias. Our approach is to derive estimates the unobserved heterogeneity responsible endogeneity/selection bias include as additional explanatory in primary equation. These are obtained through decomposition reduced form residuals. The nature allows adjustment, testing, two forms endogeneity and/or Furthermore, it incorporates roles dynamics state dependence form. Finally, we provide an empirical illustration which features our procedure highlights ability test several underlying assumptions.