摘要
Fisher判别是多元分析的一种重要方法,但该法不具稳健性,其分析结果易受异常值的干扰。本文采用投影追踪(Projection-Pursuit)的思想,从构造稳健的协差阵出发,建立一种新的能抗异常值干扰的稳健的Fisher判别方法。
Fisher discrimination is a important method
in the area of multivariate analysis,and it has
being widely used in biomedicine, geology, econ-
omics and other scientific areas. But it is non-
robust and can easily be influenced by outliers.
In this paper,we developed a new robust Fisher
discrimination procedure via the technique of
Projection-Pursuit. Results of Monte Carlo simu-
lation and practical examples showed that the
new procedure wins advantages over the cla-
ssical Fisher discrimination when some outliers
exi(?)t in data set
出处
《中国卫生统计》
CSCD
北大核心
1993年第2期16-19,共4页
Chinese Journal of Health Statistics
基金
国家自然科学基金资助项目(编号39070765)
