Identification and doubly robust estimation of nonignorable missing data.
主 题: Identification and doubly robust estimation of nonignorable missing data.
报告人: 12级苗旺博士，导师是耿直老师，方向是统计学 (理科一号楼1560)
时 间: 2016-05-26 12：00-13：15
地 点: 理科一号楼1560（研究生学术午餐会）
Missing data problems arise in many applied research studies. They may jeopardize statistical inference of the model of interest, especially when the missing mechanism is nonignorable, that is, the missingness process depends on the missing values themselves even conditional on the observed data. With nonignorable missing data, the model of interest is often not identifiable without imposing further assumptions. Identification means that the parameter of interest is uniquely determined by the observed data. Although it is fundamental for valid statistical inference, identifiability is not established for many commonly-used models. In this talk, I present our recent work on the identification problem, including results for parametric models and semiparametric models. Building on the identification conditions, if time permits, I will also talk about estimation issues, including doubly robust methods. 报名方式：请有意参加的老师在5月25日(周三)晚12点前发送邮件至smsxueshu@126.com,我们将回复邮件和您确认,邮件报名方式仅限于老师，有意参加的同学请点击报名链接http://www.sojump.hk/jq/8423523.aspx ，谢谢！