Spatial Dynamic Panel Data Models with High-Order Time-Varying Endogenous Weights Matrices

In this paper, we study the spatial dynamic panel data models with high-order time-varying endogenous weights matrices. To estimate the model, we propose a generalized method of moments (GMM) estimator. Compared to the traditional quasi-maximum likelihood (QML) estimator, GMM estimators can achieve consistency under the unknown heteroskedasticity, potentially be more efficient under homoskedasticity, and be easier to compute by avoiding the evaluation of the complicated Jacobian matrix. We further establish the asymptotic property of our proposed GMM estimators under different settings of $n$ and $T$. Monte Carlo simulations confirm that our proposed GMM estimators have satisfactory finite sample performances