Overview
- Presents an approach to characterizing the interdependencies of multivariate time series by means of the basic concept of the one-way effect
- Shows how the third-series effect is eliminated with least causal distortion, introducing partial measures of the one-way effect, reciprocity, and association
- Illustrates the proposed causal characterization by means of empirical applications to real data sets of the US macroeconomy and Japan’s financial economy
- Includes supplementary material: sn.pub/extras
Part of the book series: SpringerBriefs in Statistics (BRIEFSSTATIST)
Part of the book sub series: JSS Research Series in Statistics (JSSRES)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (5 chapters)
Keywords
About this book
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.
Reviews
“This is very nicely written book on interdependence measures between time series. The exposition is clear and the book is enriched with various examples and applications. Basic knowledge of time-series analysis is assumed. The book should trun out to be very useful for statisticians, econometricians or time-series analysts.” (Alexander M. Lindner, Mathematical Reviews, February, 2019)
Authors and Affiliations
About the authors
Kosuke Oya, Osaka University
Taro Takimoto, Kyushu University
Ryo Kinoshita, Tokyo Keizai University
Bibliographic Information
Book Title: Characterizing Interdependencies of Multiple Time Series
Book Subtitle: Theory and Applications
Authors: Yuzo Hosoya, Kosuke Oya, Taro Takimoto, Ryo Kinoshita
Series Title: SpringerBriefs in Statistics
DOI: https://doi.org/10.1007/978-981-10-6436-4
Publisher: Springer Singapore
eBook Packages: Mathematics and Statistics, Mathematics and Statistics (R0)
Copyright Information: The Author(s) 2017
Softcover ISBN: 978-981-10-6435-7Published: 08 November 2017
eBook ISBN: 978-981-10-6436-4Published: 26 October 2017
Series ISSN: 2191-544X
Series E-ISSN: 2191-5458
Edition Number: 1
Number of Pages: X, 133
Number of Illustrations: 32 b/w illustrations
Topics: Statistical Theory and Methods, Statistics for Life Sciences, Medicine, Health Sciences, Statistics for Business, Management, Economics, Finance, Insurance, Statistics for Social Sciences, Humanities, Law, Statistics and Computing/Statistics Programs, Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences