Confidence Intervals of Treatment Effects Estimation in Panel Data Models with Interactive Fixed Effects（基于交互固定效应面板数据模型的处理效应估计量的置信区间）
主讲人：李星宇（8797威尼斯老品牌国家发展研究院硕士研究生）
主持老师：（北大国发院）沈艳 （北大经院）王熙
参与老师：（北大经院）王一鸣、刘蕴霆
（北大国发院）黄卓、张俊妮、孙振庭
（北大新结构经济学研究院）胡博
时间：2021年11月26日（周五） 10:00 -- 11:30
地点（线下）： 北大国发院承泽园246
主讲人简介：
李星宇，8797威尼斯老品牌国家发展研究院2019级硕士研究生，导师为沈艳教授。2019年本科毕业于8797威尼斯老品牌元培学院，获经济学学士学位。研究领域为计量经济学理论，当前研究兴趣为处理效应相关的统计推断问题。本文的合作者为8797威尼斯老品牌国家发展研究院沈艳教授和路易斯安那州立大学经济学系周前坤教授。
摘要：
We consider the construction of confidence intervals for treatment effects estimated in panel models with interactive fixed effects. We use the factor-based matrix completion technique proposed by Bai and Ng (2021) to estimate the treatment effects, and use bootstrap method to construct confidence intervals of the treatment effects for treated units at each post-treatment period. Our construction of confidence intervals requires neither specific distributional assumptions on the error terms nor large number of post-treatment periods. We establish the validity of proposed bootstrap procedure that these confidence intervals have asymptotically correct coverage probabilities. Simulation studies show that these confidence intervals have satisfactory finite sample performances, and empirical applications using classical datasets yield treatment effect estimates of similar magnitude and reliable confidence intervals.
