[数量经济学研讨会​]Heterogenous structural breaks in panel data models

报告题目:Heterogenous structural breaks in panel data models
报告人:Ryo Okui

内容简介:In many applications, there is a good reason to suspect that structural breaks occur at different time points across individual units and the sizes of the breaks dif- fer too. This paper provides a new model and a new estimation procedure for panel data that allow us to discern heterogenous structure breaks. We model individual heterogeneity to have a grouped pattern such that individuals within the group share the same regression coefficients. For each group, we allow common structure breaks in the coefficients, while the number of breaks and the break points can differ across groups. We develop a hybrid procedure of the grouped fixed effects and adaptive group fused Lasso (least absolute shrinkage and selection operator) to estimate the model. The grouped fixed effects approach is used to estimate the group structure and the adaptive group fused Lasso is used to detect the structural breaks and obtain coefficient estimates. We show that our method can consistently identify the latent group structure, detect structural breaks, and estimate the regression parameters. Monte Carlo results demonstrate good performance of the method in finite sample. We apply our method to two cross-country empirical studies and illustrate the im- portance of taking heterogenous structural breaks into account.

报告人简介:Ryo Okui,上海纽约大学副教授,研究领域为微观计量经济学,研究论文曾发表于Econometrica, Review of Economic Studies以及其他顶级计量经济学期刊。


人大经济论坛 rdjjlt.org 人大经济论坛 bbs.econ.ruc.edu.cn