Controlling Interactive Fixed Effects with Diversified Projections

(计量、金融和大数据分析工作坊)

主讲人:Hongjun LiTsinghua University

主持老师:(北大经院王熙

参与老师:(北大经院)王一鸣、刘蕴霆、王法

(北大国发院)黄卓张俊妮、孙振庭

(北大新结构)胡博

时间:2023121日(周 10:00-11:30

地点(线 北京大学经济学院107会议室

报告摘要:

This paper considers estimation and inferential issues of panel data models with interactive fixed effects (IFE) using diversified projections (DP) method proposed recently by Fan and Liao (2022). In contrast with ordinary least square method in Bai (2009) and weighted least square method in Bai and Li (2021), our method enjoys some merits such as robustness to the pervasive conditions on factors, stationarity condition on data, or weak serial dependence. Under certain regularity conditions, we prove that the DP estimators are root NT-consistent, and have asymptotically normal distribution. We run Monte Carlo simulations to investigate the finite sample properties of the DP estimators and find its superior performance under the setup alike to real data. We apply our method to the study on the nexus of GDP growth and financial development, and find that the estimate from the DP method is more reasonable than the alternatives in the sense that it is close to the prediction of the related economic theory.

 

主讲人简介:

Hongjun Li an associate professor at Tsinghua University. His primary research interests lie in econometrics and empirical industrial organization. His expertise centers on nonparametric econometrics, machine learning, and the analysis of high-dimensional data. He has publications in Econometric Reviews, Economics Letters, Empirical Economics, and Journal of Econometrics.

 

Baidu
sogou