|
主讲人简介：
|
朱仲义，复旦大学统计系教授，博士研究生导师；曾任中国概率统计学会第八、九届副理事长,国际著名杂志”Statistica Sinica”的 副主编;现任“应用概率统计”,”数理统计与管理”杂志编委,中国现场统计研究会常务理事,中国统计教材编审委员会委员。专业研究方向为：保险精算；纵向数据(面板数据)模型；分位数回归模型等。主持完成国家自然科学基金四项、国家社会科学基金一项，作为子项目负责人完成国家自然科学基金重点项目一项。目前主持国家自然科学基金一项.近几年发表论文90多篇(其中包括在国际顶级刊物：J.R.Stat.Soc B, J.A.S.A., Ann. Statist. 和Biometrika等SCI论文五十多篇)。作为第一完成人研究成果获得教育部自然科学二等奖一次。
|
|
讲座简介：
|
This paper investigates the latent group structures in ultra high-dimensional panel data model. It is assumed that the individuals form unobserved groups, where the individual effects are the same within a group but heterogeneous across different groups. A penalized regression approach is proposed to identify the latent group structures and the important covariates simultaneously. A new ADMM-CD algorithm is proposed to optimize the objective function. When the sample sizes go to infinity, it is shown that the proposed estimator recovers the latent group structures and the important covariates in probability approaching one. The finite sample performance of the proposed estimator is evaluated through Monte Carlo studies and illustrated with a real data set |
