金融时间序列分形维估计的小波方法

讨论了金融时间序列的性质,通过实际数据说明,金融时间序列具有两个重要特性——统计自相似性和非平稳性.利用正交小波变换的方法,给出了其分形维的估计方法.最后,实证分析了国内金融市场,并应用此方法分别得出了上证综合指数序列过程和深证成分指数序列过程的分形维.

Estimating the Fractal Dimension of Financial Time Series by Wavelet

In this paper, some properties of financial time series are discussed. We claim that the statistical self|similarity and nonstationarity are two important features of financial time series by financial data. And we obtain a method estimating the fractal dimension of financial time series by the coefficients of discrete wavelet transform. It shows that wavelet transform is an effective method for analysis of the nonstationarity and statistical self|similarity. And then we analyze the feature of financial market and obtain the fractal dimension of the stock price index of Shanghai and Shenzhen with our approach.