基于变化趋势相异性的金融时间序列函数聚类分析  

Functional Cluster of Financial Time Series Based on the Difference in the Trends of Changes

作　　者：靳刘蕊[1] 

机构地区：[1]河南财经学院统计学系,河南郑州450002

出　　处：《经济经纬》2010年第2期66-69,共4页Economic Survey

摘　　要：针对函数数据聚类方法中基于序列数值模式测度相似性的聚类方法不考虑轨迹形状,而基于序列形状模式又忽略了序列数值所代表的相似信息和趋势信息,笔者提出一种对曲线之间对应里程碑出现的时间差异和所隐含的变化幅度差异的相异性测度法,据此将具有类似变化趋势的曲线聚为一类。运用该法对上证50指数的股票进行聚类分析,结果表明该聚类法能很好地测度曲线之间变化趋势的相异性,在高频金融时间序列的聚类分析中具有现实意义。The author puts forward a functional cluster method which measures the difference based on milestones and takes both sequence values and shapes into account. The method overeomes the disadvantage of the cluster methods based on sequence values ignoring the trajectory shapes and methods based on sequence shapes neglecting sequence values which involve information about similarities and trends between curves. The cluster method is of practical significance in the cluster analysis of high frequency financial time series.

关 键 词：函数聚类 金融时间序列 相异性测度 里程碑 

分 类 号：C81[社会学—统计学]