摘要
在线性回归模型的局部影响分析中,通过用具有高崩溃点的稳健估计替代局部影响分析诊断统计量中投影矩阵的方法,给出了一种有效识别影响点的方法.实例分析说明,该方法对高杠杆点及掩盖效应具有较好的识别效果.
A new method is suggested to study local influence in linear regression model by inserting a high-breakdown point estimation in projection matrix.It is shown that this method is effective to identify the joint influence and masking effects appeared in leverage points.Three examples are analyzed for illustration.
出处
《云南大学学报(自然科学版)》
CAS
CSCD
2004年第1期1-5,共5页
Journal of Yunnan University(Natural Sciences Edition)
基金
ThisresearchissupportedbyNationalNaturalScienceFoundationofChina(10261009)andScienceFoundationofYunnanProvince ( 2 0 0 0A 0 0 0 3M )