三路数据聚类方法综述  

A Review on Clustering Methods of Three-way Data

作　　者：李因果[1] 

机构地区：[1]江苏师范大学经济学院,江苏徐州221116

出　　处：《统计与信息论坛》2012年第11期27-32,共6页Journal of Statistics and Information

摘　　要：三路数据主要包含面板数据、纵向数据和三模数据三种立体数据格式。三路数据在社会科学和自然科学研究中受到越来越广泛的关注和应用。传统的聚类分析理论和方法主要基于两路平面数据而建立,对于三路数据,这些理论和方法则显得无能为力。在对传统的两路数据聚类方法做概要回顾的基础上,对国内外主流的三路数据聚类方法做了简要综述和总结。Three--way data mainly consists of three formats, such as panel data , longitudinal data and three--mode data. Three--way data has been paid more and more attention in the study of social and natural sciences and gained wide applications. Traditional theories and methods of clustering analysis were mainly established based on two--way planar data, which are powerless for three--way data. This paper firstly does a summary review of two-- way data clustering methods, then provides a brief overview of domestic and international mainstream three--way data clustering methods, and finally makes a summary about three--way data clustering methods.

关 键 词：三路数据 面板数据 纵向数据 三模数据 聚类方法 

分 类 号：O212[理学—概率论与数理统计] F222.3[理学—数学]