Analyzing multiple nonlinear time series with extended Granger causality

By Yonghong Chen, Govindan Rangarajan, Jianfeng Feng, Mingzhou Ding. 2004

397 citations recorded by the source corpus.

Identifying causal relations among simultaneously acquired signals is an important problem in multivariate time series analysis. For linear stochastic systems Granger proposed a simple procedure called the Granger causality to detect such relations. In this work we consider nonlinear extensions of Granger's idea and refer to the result as extended Granger causality. A simple approach implementing the extended Granger causality is presented and applied to multiple chaotic time series and other types of nonlinear signals. In addition, for situations with three or more time series we propose a conditional extended Granger causality measure that enables us to determine whether the causal relation between two signals is direct or mediated by another process.

Subfields: Artificial Intelligence, Economics and Econometrics, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/e4030fe6749be1f3273cb0743feb784e467b1aeb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Economics and Econometrics

In Statistical and Nonlinear Physics

Citations in the corpus

Detecting Causality in Complex Ecosystems (2012, background): “Conditional Mutual Information There is a large body of work on detecting causality in time series using the concept of conditional mutual information (CMI) and the equivalent concept of transfer entropy (55, 61-65, 67, 68).”
Causal Inference on Time Series using Structural Equation Models (2012, background): “G-causality has been extended to nonlinear relationships, [e.g. Chen et al., 2004, Ancona et al., 2004].”
Causality detection based on information-theoretic approaches in time series analysis (2007, methodology): “Another nonlinear extension of the Granger causality approach was proposed by Chen et al. [46] using local linear predictors.”
A comparative study of synchrony measures for the early diagnosis of Alzheimer's disease based on EEG (2010, neutral): “Interestingly, non-linear extensions of Granger causality have been proposed recently (see, e.g., Ancona et al., 2004; Chen et al., 2004), but we will not consider such extensions in this paper, since they are less commonly used.”
Nonlinear multivariate analysis of neurophysiological signals. (2005, background): “Recently, a further extension of nonlinear Granger causality has been proposed, which aims to detect whether the causal relation between two signals is due to direct coupling between them or due to a third system that drives them (Chen et al., 2004).”
Assessing Nonlinear Granger Causality from Multivariate Time Series (2008, methodology): “In comparison, we conducted permutation tests based on the other causality measures, i.e., extended Granger causality index (EGCI) [ 6 ], nonlinear extensions of Granger causality (NLGC) [7], and Transfer entropy (TE) [24] (Significance level 0.05).”
Nonlinear dynamical analysis of EEG and MEG: review of an emerging field. (2005, background): “A alternative approach to do this is based upon the notion of Granger causality (Chen et al., 2004).”
Causal Inference on Time Series using Restricted Structural Equation Models (2013, background): “G-causality has been extended to nonlinear G-causality, [e.g. Chen et al., 2004, Ancona et al., 2004].”
Diagnosis of Alzheimer's disease from EEG signals: where are we standing? (2010, background): “In addition, nonlinear extensions of Granger causality have recently been developed (see, e.g., [128] [129]).”