Abstract

This paper proposes an extension of principal component analysis to non-stationary multivariate time series data. A criterion for determining the number of final retained components is proposed. An advance correlation matrix is developed to evaluate dynamic relationships among the chosen components. The theoretical properties of the proposed method are given. Many simulation experiments show our approach performs well on both stationary and non-stationary data. Real data examples are also presented as illustrations. We develop four packages using the statistical software R that contain the needed functions to obtain and assess the results of the proposed method.

Details

Title
Moving dynamic principal component analysis for non-stationary multivariate time series
Author
Fayed, Alshammri 1 ; Pan Jiazhu 2 

 University of Strathclyde, Department of Mathematics and Statistics, Glasgow, UK (GRID:grid.11984.35) (ISNI:0000000121138138); Saudi Electronic University, Department of Basic Sciences, Riyadh, Kingdom of Saudi Arabia (GRID:grid.449598.d) (ISNI:0000 0004 4659 9645) 
 University of Strathclyde, Department of Mathematics and Statistics, Glasgow, UK (GRID:grid.11984.35) (ISNI:0000000121138138); Yangze Normal University, School of Mathematics and Statistics, Chongqing, China (GRID:grid.11984.35) 
Pages
2247-2287
Publication year
2021
Publication date
Sep 2021
Publisher
Springer Nature B.V.
ISSN
0943-4062
e-ISSN
1613-9658
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2550946548
Copyright
© The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.