讲座主题：Threshold spatial autoregressive model

主讲嘉宾：李鲲鹏（首都经济贸易大学国际经管学院 教授）

讲座时间：2019年5月14日（周二），14:00-15:30

讲座地点：沙河校区主教501

嘉宾简介：李鲲鹏，中共党员，国家自然科学基金优秀青年项目获得者，首都经济贸易大学国际经管学院教授、博士生导师、副管理员。研究方向为计量经济学，研究领域包括高维因子模型、交互效应面板模型、空间计量模型、断点门限模型等。在国内外知名期刊发表论文20余篇，包括Annals of Statistics、Journal of Business & Economic Statistics、Journal of Econometrics、Review of Economicsand Statistics等。现为中国数量经济学会常务理事、Journal of Business& Economic Statistics期刊编委。

内容摘要：This paper consider theestimation and inferential issues of threshold spatial autoregressive model,which is a hybrid of threshold model and spatial econometric model. We considerusing the quasi maximum likelihood (QML) method to estimate the model. Theasymptotic theory of the QML estimator is established under the setup that thethreshold effect shrinks to zero along with an increasing sample size. Ouranalysis indicates that the limiting distribution of the QML estimator for thethreshold value is pivotal up to a scale parameter which involves the skewnessand kurtosis of the errors due to the misspecification on the distribution oferrors. The QML estimators for the other parameters achieve the oracleproperty, that is, they have the same limiting distributions as the infeasibleQML estimators, which are obtained supposing that the threshold value isobserved a priori. We also consider the hypothesis testing on the presence ofthreshold effect, and the hypothesis testing on the threshold value equal tosome prespecified one. We run Monte carlo simulations to investigate the finitesample performance of the QML estimators and find that the QML estimators havegood performance.