Volume 122, Number 4, May 2018
|Number of page(s)||7|
|Published online||03 July 2018|
Multiscale horizontal-visibility-graph correlation analysis of stock time series
School of Economics and Management, Beijing Jiaotong University - Beijing 100044, PRC
Received: 17 January 2018
Accepted: 6 June 2018
This letter is devoted to measure the nonlinear interactions between non-stationary time series on multiple time scales. A graph-theoretic method by the node degrees relationship in the context of horizontal visibility graphs (HVGs) is proposed, which bridges the gap among time series analysis, multiscale analysis, and graph theory. We compare the new method with other measures, and study the degree properties and significance test. We then apply it to stock time series analysis, so as to quantify the information exchange between the daily closing price and daily trading volume in stock markets.
PACS: 05.45.Tp – Time series analysis / 89.20.-a – Interdisciplinary applications of physics / 89.75.-k – Complex systems
© EPLA, 2018
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.