摘要
将经验模式分解理论应用于金融时间序列分析中,建立了一种新的基于经验模式分解和移动平均的综合分析模型。经验模式分解基于信号的局部特征时间尺度,能把复杂的信号分解为有限个基本模式分量之和,是一种完全在时域中进行的自适应分解,克服了小波等分解分析方法中的基函数选择问题,非常适用于非线性和非平稳过程的分析。股市分析实例表明,该模型能有效提高股市波动信号的信噪比,揭示股市价格的内在运动规律,增强分析结果的可靠性,在金融时间序列分析中具有很高的应用价值。
The empirical mode decomposition (EMD)theory was introduced to financial time series analyzing, and a new method based on EMD and moving average (MA)was proposed. Any complicated signal can be decomposed into a finite and often small number of intrinsic mode functions(IMF) with the empirical mode method, which is based on the local charac- teristic time scale of the signal. The problem of the selection of base function in wavelet decomposition can be solved by this adaptive decomposition method, and it is applicable to nonlinear and non-stationary signal. The application to stock market shows that the ratio of signal to noise of the signals collected from stock market is improved, the internal moving regularity of financial time series is revealed and the result is more reliable.
出处
《天津大学学报(社会科学版)》
CSSCI
2010年第2期125-128,共4页
Journal of Tianjin University:Social Sciences
关键词
经验模式分解
移动平均
金融时间序列
技术分析
empirical mode decomposition
moving average
financial time series
technical analysis