惩罚逻辑回归的击穿点  

Breakdown point of penalized logistic regression

作　　者：董玉林 郭潇 DONG Yulin;GUO Xiao(International Institute of Finance,School of Management,University of Science and Technology of China,Hefei 230026,China)

机构地区：[1]中国科学技术大学管理学院国际金融研究院,合肥230026

出　　处：《中国科学院大学学报（中英文）》2020年第5期582-592,共11页Journal of University of Chinese Academy of Sciences

基　　金：Supported by the Fundamental Research Funds for the Central Universities and the National Natural Science Foundation of China(11601500,11671374,11771418)。

摘　　要：击穿点是估计未知参数稳健性的重要度量。在常规的低维逻辑回归模型中,极大似然估计的击穿点已有了广泛的研究,但少有对高维惩罚似然估计击穿点的分析。通过研究高维逻辑回归模型的惩罚似然估计的增加和替换击穿点来分析这个问题。特别地,证明惩罚极大似然估计的L 2范数总是有界的,这表明有限样本的击穿点达到了最大值0.5。此外,还提供了斜率参数的内爆击穿点的上界。模拟学习很好地支持了该理论结果。Breakdown point is regarded as an important measure of robustness in regression analysis.At the same time,sparse model estimation is a hot topic in data analysis.In the case of less attention to the breakdown point of robust estimates in nonlinear models,we study it in binary response models.We prove that the penalized estimate of logistic models always stays bounded,which means the finite explosive breakdown point of it is 1.Moreover,we give an upper bound of the implosive breakdown point of the slope parameter.Both simulation study and real data application verify this point while we use the approximation method and coordinate descent algorithm.

关 键 词：击穿点 逻辑回归 极大似然估计 正则化 稳健估计 

分 类 号：O212.1[理学—概率论与数理统计]