- 期刊
Evaluating the Complexity of Time Series Based on Distributional Orderliness
摘要
It is significant to study the complexity of financial time series, since the financial market is a complex dynamic system. Sample entropy (SampEn) is a widely used method to quantify the complexity of time series. However, studies showed that an increase in the SampEn may not always be associated with an increase in dynamical complexity. To deal with the problem, we proposed a modified method of SampEn to measure the complexity of complex dynamical systems. The method based on a time decay function and presented a different way of the complexity of time series. Simulations were conducted over artificial and stock time series for providing the comparative studies. Results showed that the modified method can distinguish time series from different complex systems and time series with different distributions. Furthermore, compared with SampEn, the results were more consistent with the real complexity of time series. Finally, the modified method was applied to financial time series, and get some interesting results.
延伸閱讀
- Weng, C. H. (2013). Complexity of time series [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2013.02441
- Lian, C., & Hu, J. (2020). Attention Analysis of Owners Committee: A Method for Visualizing Time Series Data. International Journal of Social Science and Education Research, 3(5), 145-154. https://doi.org/10.6918/IJOSSER.202005_3(5).0025
- Jeng, Y. N., & Cheng, Y. C. (2004). A Simple Strategy to Evaluate the Frequency Spectrum of a Time Series Data with Non-Uniform Intervals. 中國航空太空學會學刊, 36(3), 207-214. https://doi.org/10.6124/TAASRC.200409_36(3).02
- Lo, C. L. (1987). Some contributions to robust time series modelling [master's thesis, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200005662
- Wang, C. (2012). Statistical inference for some discrete-valued time series [doctoral dissertation, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200020051