Identification and estimation of spatial dynamic panel simultaneous equations models

This paper investigates the identification and estimation of spatial dynamic panel simultaneous equations models with simultaneous effects, spatial effects, and time lagged effects. The model in this paper explicitly models interactions among different economic variables with simultaneous effects. Spatial interactions are presented by spatial weight matrices and, in addition to dynamics in space and time, we allow both individual and time fixed effects. For estimation, we study asymptotic properties of quasi-maximum likelihood estimators with large spatial units n and time periods T and IV-based estimators with large or small T. Finite sample properties of these estimators are studied using Monte Carlo experiments.