讲座人简介：

李海奇，湖南大学金融与统计学院教授、博士生导师、副院长，曾任美国康奈尔大学经济学系访问学者(2014.8-2015.8)。目前研究方向为金融计量经济学、金融工程和数字经济，研究成果发表于经济学国际顶尖和权威期刊以及中文重点期刊，如Journal of Econometrics，Econometric Reviews，《数量经济技术经济研究》《统计研究》《中国管理科学》等。曾主持湖南省自然科学基金杰出青年项目、国家自然科学基金项目、教育部人文社科规划基金项目等多项国家和省部级科研项目。曾获得湖南大学科研标兵、湖南大学优秀教师等荣誉或奖励。

讲座简介：

Structural change is a long-standing problem in time series econometrics. Macroeconomic and financial time series are likely to suffer from structural instability due to changes in preferences, technologies, and policies, among other factors. Most studies on moment condition models assume that structural parameters are time-invariant over the entire sample period. To allow for timevarying structural parameters in high-dimensional moment condition models, this study proposes a shrinkage local generalized method of moments (SLGMM) that simultaneously achieves parameter estimation and moment selection. We show that the proposed method consistently selects the correct moment conditions and the SLGMM estimator possesses the oracle property; it is asymptotically as efficient as the time-varying GMM estimator based on all valid moment conditions. Moreover, the SLGMM estimator is consistent and with proper standardization it asymptotically follows a normal distribution. A Monte Carlo simulation study and an empirical application on the New Keynesian Phillips curve are conducted to demonstrate the merits of the newly proposed method.