【主讲】Kunpeng Li (Capital University of Economics and Business)
【主题】Dynamic Spatial Panel Data Models with Common Shocks
【时间】2017年9月28日 (周四) 15：30-17：00
【地点】上海财经大学经济学院楼701室
【语言】英文
【摘要】Real data often have complicated correlation over cross section and time. Modeling, estimating and interpreting the correlations in data are particularly important in economic analysis. This paper integrates several correlation-modeling techniques and propose dynamic spatial panel data models with common shocks to accommodate possibly complicated correlation structure over cross section and time. A large number of incidental parameters exist within the model. The quasi maximum likelihood method (ML) is proposed to estimate the model. Heteroskedasticity is explicitly estimated. The asymptotic properties of the quasi maximum likelihood estimator (MLE) are investigated. Our analysis indicates that the MLE has a nonnegligible bias. We propose a bias correction method for the MLE. The simulations further reveal the excellent finite sample properties of the quasi-MLE after bias correction.
