报告题目:Almost Uniform Bias Correction for Persistent Panel Local Projections
报 告 人:Geert Dhaene
报告时间: 2026年04月10日(周五)15:40-17:00
报告地点:博学楼 I-206
主办单位:高等经济研究院
【报告人简介】
Geert Dhaene,鲁汶大学(KU Leuven)计量经济学荣休教授。他的研究涵盖计量经济理论与应用方法,尤其关注面板数据模型、非线性估计及冗余参数等问题。Dhaene教授在计量经济学领域的学术贡献广受认可,其研究成果发表于Econometrica、The Review of Economic Studies、Journal of Econometrics、Econometric Theory 等国际顶级期刊。
【内容摘要】
Panel local projections are widely used for impulse response estimation in policy analysis, with the within-group (WG) estimator being the default estimator. This paper studies the properties of the WG estimator and two bias-corrected estimators: the analytical bias correction of Herbst and Johannson (2024) and the half-panel jackknife (HPJ) bias correction suggested by Mei, Sheng, and Shi (2026). Our setup considers an autoregressive control variable that is potentially persistent, with varying degrees of persistence. We show that the two bias corrections are not uniformly valid when the data are persistent. The Herbst and Johannson (2024) bias correction is not valid whenever the autoregressive parameter drifts sufficiently quickly to one. The HPJ bias correction is not valid when the autoregressive parameter is local-to-unity, but remains valid when it drifts to one more slowly or more quickly. In addition, we propose novel standard errors for the HPJ estimator that yield confidence intervals with much better coverage properties.
【更多信息】
获取更多信息,请扫描下方二维码加入“IAER Seminar”腾讯QQ群(群号:904 544 292)或微信群,可同时关注高等经济研究院网站:https://iaer.dufe.edu.cn。

撰稿:王杰 审核:崔惠玉 单位:高等经济研究院