东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2010, Vol. 31 ›› Issue (4): 605-608.DOI: -

• 论著 • 上一篇    

期货价格收益序列的多重分形统计描述及成因分析

苑莹;庄新田;金秀;   

  1. 东北大学工商管理学院;
  • 收稿日期:2013-06-20 修回日期:2013-06-20 出版日期:2010-04-15 发布日期:2013-06-20
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(70901017,70871022,70771023);;

Multifractal statistical description and its sources for time series of returns on futures price

Yuan, Ying (1); Zhuang, Xin-Tian (1); Jin, Xiu (1)   

  1. (1) School of Business Administration, Northeastern University, Shenyang 110004, China
  • Received:2013-06-20 Revised:2013-06-20 Online:2010-04-15 Published:2013-06-20
  • Contact: Yuan, Y.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

881

摘要： 运用多重分形消除趋势波动分析方法,对之前较少被研究的中国铜和大豆两个期货品种的价格收益序列进行实证研究.结果表明,两种期货价格收益序列具有尖峰态特征,不服从正态分布,且二者均存在明显的多重分形特征,仅用单一的标度指数对其进行描述是不充分的.进一步对其多重分形成因进行分析,发现期货价格收益序列的多重分形特征主要是由收益序列的波动相关性引起的,该相关性导致了价格的有偏随机游走,市场未达到弱式有效.

关键词: 资本市场复杂性, 消除趋势波动分析, 期货价格, 时间序列, 弱式有效

Abstract: According to the multifractal detrended fluctuation analysis, an investigation on the time series of returns on the copper and soy bean futures prices in China was done empirically. It was found that the time series of returns on both futures prices are characterized with the leptokurtic especially the multifractality and not distributed normally, thus indicating that a single-scale index is insufficient to describe the commodity futures price fluctuation. Furthermore, the cause of multifractality was analyzed and it was found that most multifractality of the data is due to different long-range correlations for either small or large fluctuation. This correlations result in the price return series to be a biased random walk, i.e. the stock market fails to reach the soft efficiency.

中图分类号: