时间序列超扩散行为的检测
On the detection of superdiffusive behaviour in time series
摘要:
我们提出了一种新的方法来检测superdiffusive行为,并确定超扩散率的时间序列数据。我们的方法同样适用于随机和确定性的时间序列数据(不需要先验知识的性质的数据),并依赖于一个实现(即一个样本路径)的过程。线性漂移效应会自动消除,无需任何预处理。我们展示了从独立同分布构造的时间序列的数值结果。$α$ -稳定随机变量和确定性弱混沌映射。我们比较我们的方法与标准的方法估计的增长率的均方位移,以及$p$的变化方法,极大似然,分位数匹配和线性回归的经验特征函数。
英文摘要:
We present a new method for detecting superdiffusive behaviour and for determining rates of superdiffusion in time series data. Our method applies equally to stochastic and deterministic time series data (with no prior knowledge required of the nature of the data) and relies on one realisation (ie one sample path) of the process. Linear drift effects are automatically removed without any preprocessing. We show numerical results for time series constructed from i.i.d. $α$-stable random variables and from deterministic weakly chaotic maps. We compare our method with the standard method of estimating the growth rate of the mean-square displacement as well as the $p$-variation method, maximum likelihood, quantile matching and linear regression of the empirical characteristic function.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。