A Computationally Practical Simulation Estimation Algorithm for Dynamic Panel Data Models with Unobserved Endogenous State Variables, International Economic Review, forthcoming

This paper develops a simulation estimation algorithm that is particularly useful for estimating dynamic panel data models with unobserved endogenous state variables. The new approach can easily deal with the commonly encoun-tered and widely discussed initial conditions problem, as well as the more general problem of missing state variables during the sample period. Repeated sampling experiments on dynamic panel data probit models with serially corre-lated errors indicate that the estimator has good small sample properties. We also apply the estimator to a model of female labor force participation decisions using PSID data with serious missing data problems