【主讲】韩晓祎 (厦门大学)
【主题】Bayesian Analysis of Spatial Panel Autoregressive Models with Time-varying Endogenous Spatial Weight Matrices and Common Factors
【时间】2015年3月13日 (周五) 15：30-17：00
【地点】上海财经大学经济学院楼602室
【语言】英文
【摘要】This paper examines the specification and estimation of spatial panel autoregressive (SAR) models with dynamic, time-varying endogenous spatial weights matrices and common factors. Motivated by the spillover effects of state Medicaid spending on welfare programs, we combine the features of endogenous time-varying weights matrices and common factors for the first time in the SAR panel models. In this particular application, endogeneity of the spatial weights matrices comes from the correlation of economic distance" and the disturbances in the SAR equation. Common factors are introduced to control for common shocks to all states and factor loadings may capture heterogeneity in states' responses. For the estimation, the Bayesian MCMC method is developed. Identification of factors and factor loadings, and the corresponding model selection issues based upon the Bayes factor and the deviance information criterion (DIC) are also explored. We find that a state's Medicaid related spending is positively and significantly affected by the Medicaid related spending of its neighbors. Furthermore, in the context of Medicaid spending, both welfare motivated move and yardstick competition are possible sources of strategic interactions among state governments. And welfare motivated move turns out to be a more important driving force of the interdependence of state spending policy.
