Characterizing Interdependencies of Multiple Time Series : Theory and Applications. 1st ed. 2017

種類:

電子ブック

責任表示:

by Yuzo Hosoya, Kosuke Oya, Taro Takimoto, Ryo Kinoshita

出版情報:

Singapore : Springer Nature Singapore : Imprint: Springer, 2017

著者名:

• Hosoya, Yuzo.
• Oya, Kosuke.
• Takimoto, Taro.
• Kinoshita, Ryo.
• SpringerLink (Online service)

シリーズ名:

JSS Research Series in Statistics ;

ISBN:

9789811064364 [9811064369]    

注記:

1: Introduction to statistical causal analysis -- 2: Measures of one-way effect, reciprocity and association -- 3: Partial measures of interdependence -- 4: Inference based on the vector autoregressive and moving average model -- 5: Inference on change in causality measures -- 6: Simulation performance of estimation methods -- 7: Empirical analysis of macroeconomic series -- 8: Empirical analysis of change in causality measures -- 9: Conclusion -- Appendix -- References -- Index.
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 i

ローカル注記:

学内専用E-BOOKS (local access only)