A nonlinear generalization of spectral granger causality

Fei He, Hua Liang Wei, Stephen A. Billings, Ptolemaios G. Sarrigiannis

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Spectral measures of linear Granger causality have been widely applied to study the causal connectivity between time series data in neuroscience, biology, and economics. Traditional Granger causality measures are based on linear autoregressive with exogenous (ARX) inputs models of time series data, which cannot truly reveal nonlinear effects in the data especially in the frequency domain. In this study, it is shown that the classical Geweke's spectral causality measure can be explicitly linked with the output spectra of corresponding restricted and unrestricted time-domain models. The latter representation is then generalized to nonlinear bivariate signals and for the first time nonlinear causality analysis in the frequency domain. This is achieved by using the nonlinear ARX (NARX) modeling of signals, and decomposition of the recently defined output frequency response function which is related to the NARX model.

Original languageEnglish
Article number6725625
Pages (from-to)1693-1701
Number of pages9
JournalIEEE Transactions on Biomedical Engineering
Volume61
Issue number6
DOIs
Publication statusPublished - 27 Jan 2014
Externally publishedYes

Fingerprint

Time series
Nonlinear analysis
Frequency response
Decomposition
Economics

Keywords

  • Electroencephalogram (EEG)
  • frequency response function (FRF)
  • Granger causality
  • nonlinear systems
  • spectral analysis

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

A nonlinear generalization of spectral granger causality. / He, Fei; Wei, Hua Liang; Billings, Stephen A.; Sarrigiannis, Ptolemaios G.

In: IEEE Transactions on Biomedical Engineering, Vol. 61, No. 6, 6725625, 27.01.2014, p. 1693-1701.

Research output: Contribution to journalArticle

He, Fei ; Wei, Hua Liang ; Billings, Stephen A. ; Sarrigiannis, Ptolemaios G. / A nonlinear generalization of spectral granger causality. In: IEEE Transactions on Biomedical Engineering. 2014 ; Vol. 61, No. 6. pp. 1693-1701.
@article{f21e54b880a44f0582185307f339315d,
title = "A nonlinear generalization of spectral granger causality",
abstract = "Spectral measures of linear Granger causality have been widely applied to study the causal connectivity between time series data in neuroscience, biology, and economics. Traditional Granger causality measures are based on linear autoregressive with exogenous (ARX) inputs models of time series data, which cannot truly reveal nonlinear effects in the data especially in the frequency domain. In this study, it is shown that the classical Geweke's spectral causality measure can be explicitly linked with the output spectra of corresponding restricted and unrestricted time-domain models. The latter representation is then generalized to nonlinear bivariate signals and for the first time nonlinear causality analysis in the frequency domain. This is achieved by using the nonlinear ARX (NARX) modeling of signals, and decomposition of the recently defined output frequency response function which is related to the NARX model.",
keywords = "Electroencephalogram (EEG), frequency response function (FRF), Granger causality, nonlinear systems, spectral analysis",
author = "Fei He and Wei, {Hua Liang} and Billings, {Stephen A.} and Sarrigiannis, {Ptolemaios G.}",
year = "2014",
month = "1",
day = "27",
doi = "10.1109/TBME.2014.2300636",
language = "English",
volume = "61",
pages = "1693--1701",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "Institute of Electrical and Electronics Engineers",
number = "6",

}

TY - JOUR

T1 - A nonlinear generalization of spectral granger causality

AU - He, Fei

AU - Wei, Hua Liang

AU - Billings, Stephen A.

AU - Sarrigiannis, Ptolemaios G.

PY - 2014/1/27

Y1 - 2014/1/27

N2 - Spectral measures of linear Granger causality have been widely applied to study the causal connectivity between time series data in neuroscience, biology, and economics. Traditional Granger causality measures are based on linear autoregressive with exogenous (ARX) inputs models of time series data, which cannot truly reveal nonlinear effects in the data especially in the frequency domain. In this study, it is shown that the classical Geweke's spectral causality measure can be explicitly linked with the output spectra of corresponding restricted and unrestricted time-domain models. The latter representation is then generalized to nonlinear bivariate signals and for the first time nonlinear causality analysis in the frequency domain. This is achieved by using the nonlinear ARX (NARX) modeling of signals, and decomposition of the recently defined output frequency response function which is related to the NARX model.

AB - Spectral measures of linear Granger causality have been widely applied to study the causal connectivity between time series data in neuroscience, biology, and economics. Traditional Granger causality measures are based on linear autoregressive with exogenous (ARX) inputs models of time series data, which cannot truly reveal nonlinear effects in the data especially in the frequency domain. In this study, it is shown that the classical Geweke's spectral causality measure can be explicitly linked with the output spectra of corresponding restricted and unrestricted time-domain models. The latter representation is then generalized to nonlinear bivariate signals and for the first time nonlinear causality analysis in the frequency domain. This is achieved by using the nonlinear ARX (NARX) modeling of signals, and decomposition of the recently defined output frequency response function which is related to the NARX model.

KW - Electroencephalogram (EEG)

KW - frequency response function (FRF)

KW - Granger causality

KW - nonlinear systems

KW - spectral analysis

UR - http://www.scopus.com/inward/record.url?scp=84901268752&partnerID=8YFLogxK

U2 - 10.1109/TBME.2014.2300636

DO - 10.1109/TBME.2014.2300636

M3 - Article

VL - 61

SP - 1693

EP - 1701

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 6

M1 - 6725625

ER -