PROJECTION-PURSUIT BASED PRINCIPAL COMPONENT ANALYSIS:A LARGE SAMPLE THEORY

被引：0

作者：

Jian ZHANG Institute of MathematicsStatistics and Actuarial ScienceUniversity of KentCanterburyKent CT NFUK ^{[2
,7
]}

Institute of Systems ScienceAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing China ^{[100080
]}

机构：

来源：

JournalofSystemsScience&Complexity | 2006年 / 03期

关键词：

Dispersion matrices; eigenvalues and eigenvectors; empirical processes; principal component analysis; projection pursuit(PP);

D O I：

暂无

中图分类号：

O212 [数理统计];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

<正> The principal component analysis(PCA(is one of the most celebrated methods in analysingmultivariate data.An effort of extending PCA is projection pursuit(PP),a more general class ofdimension-reduction techniques.However,the application of this extended procedure is often hamperedby its complexity in computation and by lack of some appropriate theory.In this paper,by use of theempirical processes we established a large sample theory for the robust PP estimators of the principalcomponents and dispersion matrix.

引用

页码：365 / 385

页数：21