A0338
Title: Dynamic spatial panel data models with interactive fixed effects
Authors: Liyao Li - East China Normal University (China) [presenting]
Abstract: An M-estimation method is proposed for estimating dynamic spatial panel data models with interactive fixed effects based on (relatively) short panels. Unbiased estimating functions (EF) are obtained by adjusting the concentrated conditional quasi scores, given initial values and with factor loadings being concentrated out, to account for the effects of conditioning and concentration. Solving the estimating equations gives M-estimators of common parameters and factor parameters. Under fixed T, $\sqrt{n}$-consistency and joint asymptotic normality of both sets of M-estimators are established; under $T=o(n)$, the M-estimators of common parameters are shown to be $\sqrt{nT}$-consistent and asymptotically normal. For inference, EF is decomposed into a sum of n nearly uncorrelated terms. Outer products of these n terms, together with a covariance adjustment, lead to a consistent estimator of the VC matrix under both fixed T and $T=o(n)$. Important extensions of the methods, allowing for unknown heteroskedasticity, time-varying spatial weight matrices, and high-order dynamic and spatial effects, are critically discussed. Monte Carlo results show that the proposed methods perform well in finite samples and outperform the existing methods when T is not large.