Intrinsic superstatistical components of financial time series
Intrinsic superstatistical components of financial time series
复制标题
金融时间序列的内在超统计成分
DOI：
10.1140/epjb/e2014-50596-y
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
M. Craciun
中科院分区：
文献类型：
--
作者：
C. Vamos;M. Craciun
由复杂的层次系统生成的时间序列在不同的时间尺度上表现出各种类型的动态。金融时间序列就是这种多尺度结构的一个例子，时间尺度从几分钟到几年不等。在本文中，我们将金融指数的波动性分解为五个内在组成部分，并表明它具有异质的规模结构。小规模成分具有随机性，99% 的时间都是独立的，在金融崩溃期间变得同步，并增强了波动性分布的重尾部分。大规模成分的确定性行为与金融市场演化的非平稳性有关。我们对金融波动性的分解是一个超统计模型，比通常仅限于在完全分离的时间尺度上叠加两个独立统计数据的模型更为复杂。
Time series generated by a complex hierarchical system exhibit various types of dynamics at different time scales. A financial time series is an example of such a multiscale structure with time scales ranging from minutes to several years. In this paper we decompose the volatility of financial indices into five intrinsic components and we show that it has a heterogeneous scale structure. The small-scale components have a stochastic nature and they are independent 99% of the time, becoming synchronized during financial crashes and enhancing the heavy tails of the volatility distribution. The deterministic behavior of the large-scale components is related to the nonstationarity of the financial markets evolution. Our decomposition of the financial volatility is a superstatistical model more complex than those usually limited to a superposition of two independent statistics at well-separated time scales.