股市时间序列的多重分形分析  

Multifractal Analysis of Stock Market Time Series

作　　者：于建玲[1] 臧保将[1] 商朋见[1] 

机构地区：[1]北京交通大学理学院,北京100044

出　　处：《北京交通大学学报》2006年第6期69-72,共4页JOURNAL OF BEIJING JIAOTONG UNIVERSITY

基　　金：科技部"973"基金资助项目(2004CB318005)

摘　　要：通过对幂谱和统计矩函数的分析,得出股票市场时间序列的无标度性.借助配分函数、广义分形维数和多重分形谱对股票市场进行研究,结果表明,股票市场时间序列具有多重分形特征.这将为多重分形在金融理论方面的研究提供重要的理论基础.Power spectrum analysis and statistical moment function on a range of scales revealed scaling qualities of the date from stock market. In addition, partition function, generalized dimension function and multifractal spectrum are employed in studying the stock market to display the degree of multifractality in the time series. This will provide an important theoretic foundation for researching multifractality in the theory of finance.

关 键 词：股票市场 多重分形谱 无标度性 配分函数 广义分形维数 

分 类 号：O221.61[理学—运筹学与控制论]