Refined GMM Estimators for Simultaneous Equations Models with Network Interactions

The paper proposes a refinement of the generalized spatial two-stage and threestage least squares estimators for simultaneous systems of equations with network interdependence, recently introduced in Drukker, Egger and Prucha (2022). Specifically, we propose a refined weighting of the moment conditions underlying those estimators. Monte Carlo simulations document that the refined weighting potentially achieves non-trivial reductions in the root mean-squared errors for the network parameters of interest