Identification of treatment effects using control functions in models with continuous, endogenous treatment and heterogeneous effects

被引:116
作者
Florens, J. P. [1 ]
Heckman, J. J. [2 ]
Meghir, C. [3 ,4 ]
Vytlacil, E. [5 ]
机构
[1] Univ Toulouse 1, Inst Econ Ind, F-3100 Toulouse, France
[2] Univ Chicago, Dept Econ, Chicago, IL 60637 USA
[3] UCL, Inst Fiscal Studies, London WC1E 6BT, England
[4] UCL, Dept Econ, London WC1E 6BT, England
[5] Yale Univ, Dept Econ, New Haven, CT 06511 USA
基金
美国国家科学基金会; 英国经济与社会研究理事会;
关键词
continuous treatments; endogenous treatments; heterogeneous treatment effects; identification; nonseparable models; control function;
D O I
10.3982/ECTA5317
中图分类号
F [经济];
学科分类号
02 ;
摘要
We use the control function approach to identify the average treatment effect and the effect of treatment on the treated in models with a continuous endogenous regressor whose impact is heterogeneous. We assume a stochastic polynomial restriction on the form of the heterogeneity, but unlike alternative nonparametric control function approaches, our approach does not require large support assumptions.
引用
收藏
页码:1191 / 1206
页数:16
相关论文
共 36 条