Propensity Score of Propensity Score Methods in Estimating Treatment Effect
Holder： Mingfeng Zhan (Capital University of Economics and Business)
Time：2024-03-21 15:10-17:00
Location：Room 217, Guanghua Building 2
Abstract:
The estimation of the propensity score is vital to the inverse probability weighting (IPW) treatment effect estimators. This paper proposes a new method, termed as propensity score of propensity score (PSPS), to estimate the propensity score by observing the fact that the propensity score can be expressed as the conditional expectation of the treatment variable given the propensity score. A two-step estimation procedure is proposed and the asymptotic normality results are derived for both of the IPW average and quantile treatment effect estimators. We show that the proposed estimators can attain the efficiency bound with respect to the propensity score. In both simulation studies and real data analysis, the proposed methods are found to improve the finite sample performance of the IPW treatment effect estimators.
About the Speaker:
詹铭峰，首都经济贸易大学统计学院经济统计系讲师，厦门大学统计学博士。研究方向为政策评估，非参数计量。
Your participation is warmly welcomed!
欢迎扫码关注北大统计科学中心公众号，了解更多讲座信息!
