Price time series long memory analysis and prediction study.

Xiaobing Cheng; Mingping Xia; Ruikai Pan; Daoping Wang

Author(s)

Xiaobing Cheng College of Automation, Beijing Union University, Beijing, China

Mingping Xia College of Automation, Beijing Union University, Beijing, China

Ruikai Pan School of Chemistry and Biology, Taiyuan University of Science and Technology, Taiyuan, China

Daoping Wang School of Economic and Management, University of Science & Technology Beijing, China

Abstract

The R/S test has been extensively used in testing the long memory of financial time series, but little attentions have been paid on its validity. The paper sets the chemical raw materials styrene price time series as an example, to test the stable of the price series. It indicates that we should give prudent explanation for the R/S test, and then establish the ARFIMA model to determine the data generation process with fractal characteristics. Thus the fractal theory can be used to describe the price time series and provide theoretical support for the price time series forecasting.

Publication Details

Page(s) 241-247

DOI DOI not available

Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 49, Issue: 1, Year: 2013

Request the full text from PASTIC