财务、会计Seminar第一百五十四期讲座

演讲题目:Panel data, fixed effects, and the jackknife  

 

 

演讲者:    Geert Dhaene

 

 

演讲时间:2017325日(周六)上午10001130

 

 

演讲地点嘉庚二205

 

 

主持人:吴红军 副教授

 

 

参加者:对会计、财务研究有兴趣的师生

 

 

讲座内容简介:It  is well known that maximum likelihood estimation of nonlinear panel models with  fixed effects produce estimates that suffer from large biases and confidence  intervals with poor coverage. The jackknife offers a simple method to reduce  this bias and to obtain confidence intervals that are correctly centered under  rectangular-array asymptotics. By splitting the panel into blocks, the method is  explicitly designed to handle dynamics in the data, and yields estimators that  are straightforward to implement and can be readily applied to a range of models  and estimands. We provide distribution theory for estimators of model parameters  and average effects, present validity tests for the jackknife, and consider  extensions to higher-order bias correction and to two-step estimation problems.  (Based on joint work with Koen Jochmans, Sciences Po)