讲座：Matching Points: Supplementing Instruments with Covariates in Triangular Models
题 目：Matching Points: Supplementing Instruments with Covariates in Triangular Models
嘉 宾：Junlong Feng, Ph.D. Candidate, Columbia University
主持人：瞿茜 副教授 上海交通大学安泰经济与管理学院
时 间：2019 年 12 月 23 日（周一） 9:30-11:00
地 点：上海交通大学 徐汇校区包图 A407
We consider triangular models with a discrete endogenous variable and an instrumental variable (IV) taking on fewer values. Addressing the failure of the order condition, we develop the first approach to restore identification for both separable and nonseparable models in this case by supplementing the IV with covariates, allowed to enter the model in an arbitrary way. For the separable model, we show that it satisfies a system of linear equations, yielding a simple identification condition and a closed-form estimator. For the nonseparable model, we develop a new identification argument by exploiting its continuity and monotonicity, leading to weak sufficient conditions for global identification. Built on it, we propose a uniformly consistent and asymptotically normal sieve estimator. We apply our approach to an empirical application of the return to education with a binary IV. Though under-identified by the IV alone, we obtain results consistent with the literature using our approach.
Junlong Feng is a Ph.D. candidate from the Department of Economics at Columbia University. His research interests lie in econometrics, applied microeconomics, causal inference and machine learning.