【国际经贸学院讲座】Instrumental Variables Quantile Regression with Censoring
来源：上海立信会计金融学院 点击率：
讲座主题：Instrumental Variables Quantile Regression with Censoring 主 讲 人：陈松年 香港科技大学首席教授 讲座时间：2016年11月9日（周三）13:00 讲座地点：浦东校区五号教学楼404会议室 讲座摘要：For the quantile regression with endogeneity, Chernozhukov and Hansen (2006, 2008) developed the instrumental variables quantile regression estimator (IVQR). When censoring and endogeneity are both present, however, no practically effective instrumental variable quantile regression procedures are available, unless very strong restrictions are imposed on the exact nature of the endogeneity. In this paper, in a general setting without imposing any condition on the nature of endogeneity, we develop the sequential instrumental variable censored quantile regression procedure (SIVCQR) for the family of structural quantile regression coefficients. Our SIVCQR estimator is simple to implement in typical applications. By effectively transforming the difficult instrumental variable censored quantile regression into more standard instrumental variable quantile regression (IVQR), our estimation approach makes the instrumental variable quantile regression techniques for censored data readily accessible to applied researchers. In addition, the sequential nature of our new procedure expands the quantile range for which the structural quantile regression coefficients can be recovered, especially for the tail quantile coefficients, which may precisely be of most interest to applied researchers. We provide large sample properties of the SIVCQR. Simulation results show that our estimator performs well. 主讲人简介： 陈松年(Songnian Chen)教授，1994年毕业于普林斯顿大学(Princeton University)经济学系，获经济学博士学位，现为香港科技大学首席教授(Chair Professor)，国际知名的计量经济学家。陈教授在计量经济学特别是微观计量经济学领域造诣深厚，其在删失回归、样本选择模型、半参数变换模型、分位数回归等领域的研究享誉国际。陈教授已在Econometrica、Review of Economic Studies、Journal of Econometrics、Journal of American Statistical Association,、Annals of Statistics等国际顶级学术期刊发表论文数十篇。自2002年起任Journal of Econometrics的Fellow、副主编。 国际经贸学院 2016年11月7日
分享到：
|
