Search for content and authors
 

Granger causality, transfer entropy and GARCH models for financial time series

Ewa M. Syczewska 1Zbigniew R. Struzik 2

1. Warsaw School of Economics, Al. Niepodległości 162, Warsaw 02-554, Poland
2. The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

Abstract

There exist several tools for the assessment of possible causality in the Granger sense between two or more variables. Causality tests based on entropy transfer have been proposed e.g. by Schreiber (2000), Hlavackova et al. (2007) and by Barnett and Seth (2014) (see Syczewska and Struzik (2014)). In our earlier research causal relationship between financial variables has been shown for returns of bilateral exchange rates and stock indices. Prefiltering of the series with ARMA-GARCH type models is recommended in financial literature (Kliber (2011), Fiszeder and Orzeszko (2012), among others). This approach will be applied for the same variables, to updated time series data. The results of the Granger causality test and the nonlinear Diks-Panchenko test are compared with the results of the transfer-entropy method of causality assessment for the same variables.  

 

Legal notice
  • Legal notice:
 

Related papers

Presentation: Oral at Econophysics Colloquium 2017, Symposium C, by Ewa M. Syczewska
See On-line Journal of Econophysics Colloquium 2017

Submitted: 2017-03-16 11:48
Revised:   2017-03-16 11:48