Characterizing Interdependencies of Multiple Time Series JSS Research Series in Statistics

Characterizing Interdependencies of Multiple Time Series JSS Research Series in Statistics Theory and Applications - SpringerBriefs in Statistics

1st Edition 2017

Paperback (08 Nov 2017)

Not available for sale

Includes delivery to the United States

Out of stock

This service is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Publisher's Synopsis

This book introduces academic researchers and professionals to the basic concepts and methods for characterizing interdependencies of multiple time series in the frequency domain. Detecting causal directions between a pair of time series and the extent of their effects, as well as testing the non existence of a feedback relation between them, have constituted major focal points in multiple time series analysis since Granger introduced the celebrated definition of causality in view of prediction improvement.

Causality analysis has since been widely applied in many disciplines. Although most analyses are conducted from the perspective of the time domain, a frequency domain method introduced in this book sheds new light on another aspect that disentangles the interdependencies between multiple time series in terms of long-term or short-term effects, quantitatively characterizing them. The frequency domain method includes the Granger noncausality test as a special case.

Chapters 2 and 3 of the book introduce an improved version of the basic concepts for measuring the one-way effect, reciprocity, and association of multiple time series, which were originally proposed by Hosoya. Then the statistical inferences of these measures are presented, with a focus on the stationary multivariate autoregressive moving-average processes, which include the estimation and test of causality change. Empirical analyses are provided to illustrate what alternative aspects are detected and how the methods introduced here can be conveniently applied. Most of the materials in Chapters 4 and 5 are based on the authors' latest research work. Subsidiary items are collected in the Appendix.

Book information

ISBN: 9789811064357
Publisher: Springer Nature Singapore
Imprint: Springer
Pub date:
Edition: 1st Edition 2017
Language: English
Number of pages: 133
Weight: 213g
Height: 235mm
Width: 155mm
Spine width: 8mm