Similarity Analysis Based on Bose-Einstein Divergences for Financial Time Series

作者: Ryszard Szupiluk , Tomasz Ząbkowski

DOI: 10.1007/978-3-642-37213-1_43

关键词:

摘要: Similarity assessment between financial time series is one of problems where the proper methodological choice very important. The typical correlation approach can lead to misleading results. Often similarity measure opposite visual observations, expert’s knowledge and even a common sense. reasons that be associated with properties its adequateness for analyzed data, as well in terms aspects. In this article, we indicate disadvantages use assess propose an alternative solution based on divergence measures. particular, focus Bose-Einstein divergence. practical experiments conducted simulated real data confirmed our concept.

参考文章(13)
Andrzej Cichocki, Rafal Zdunek, Shun-ichi Amari, Csiszár’s Divergences for Non-negative Matrix Factorization: Family of New Algorithms Independent Component Analysis and Blind Signal Separation. pp. 32- 39 ,(2006) , 10.1007/11679363_5
Gennady Samorodnitsky, Murad S. Taqqu, Stable Non-Gaussian Random Processes Journal of the American Statistical Association. ,vol. 90, pp. 805- ,(1995) , 10.1201/9780203738818
Allan Kardec Barros, José Carlos Príncipe, Deniz Erdogmus, Guest Editorial: Independent Component Analysis and Blind Source Separation Signal Processing. ,vol. 87, pp. 1817- 1818 ,(2007) , 10.1016/J.SIGPRO.2007.03.013
F. J. Anscombe, Graphs in Statistical Analysis The American Statistician. ,vol. 27, pp. 17- 21 ,(1973) , 10.1080/00031305.1973.10478966
J.-F. Cardoso, P. Comon, Independent component analysis, a survey of some algebraic methods international symposium on circuits and systems. ,vol. 2, pp. 93- 96 ,(1996) , 10.1109/ISCAS.1996.540360
Joseph Lee Rodgers, W. Alan Nicewander, Thirteen ways to look at the correlation coefficient The American Statistician. ,vol. 42, pp. 59- 66 ,(1988) , 10.1080/00031305.1988.10475524