Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
5102815 | Physica A: Statistical Mechanics and its Applications | 2017 | 16 Pages |
Abstract
Transfer entropy (TE) now is widely used in the data mining and economic field. However, TE itself demands that time series intend to be stationary and meet Markov condition. Naturally, we are interested in investigating the effect of the nonlinear transformation of the two series on the TE. Therefore, the paper is designed to study the TE of five nonlinear “volatile” transformations based on the data which are generated by the linear modeling and the logistic maps modeling, as well as the dataset that come from financial markets. With only one of the TE of nonlinear transformations fluctuating around the TE of original series, the TE of others all have increased with different degrees.
Related Topics
Physical Sciences and Engineering
Mathematics
Mathematical Physics
Authors
Zhenyu Wu, Pengjian Shang,