Granger causality analysis with nonuniform sampling and its application to pulse-coupled nonlinear dynamics

Yaoyu Zhang, Yanyang Xiao, Doug Zhou, David Cai

Research output: Contribution to journalArticle

Abstract

The Granger causality (GC) analysis is an effective approach to infer causal relations for time series. However, for data obtained by uniform sampling (i.e., with an equal sampling time interval), it is known that GC can yield unreliable causal inference due to aliasing if the sampling rate is not sufficiently high. To solve this unreliability issue, we consider the nonuniform sampling scheme as it can mitigate against aliasing. By developing an unbiased estimation of power spectral density of nonuniformly sampled time series, we establish a framework of spectrum-based nonparametric GC analysis. Applying this framework to a general class of pulse-coupled nonlinear networks and utilizing some particular spectral structure possessed by these nonlinear network data, we demonstrate that, for such nonlinear networks with nonuniformly sampled data, reliable GC inference can be achieved at a low nonuniform mean sampling rate at which the traditional uniform sampling GC may lead to spurious causal inference.

Original languageEnglish (US)
Article number042217
JournalPhysical Review E
Volume93
Issue number4
DOIs
StatePublished - Apr 26 2016

Fingerprint

Nonuniform Sampling
Granger Causality
Nonlinear Dynamics
sampling
Causal Inference
pulses
inference
Aliasing
Time series
Unbiased Estimation
Power Spectral Density
Interval
intervals
Demonstrate

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Statistical and Nonlinear Physics
  • Statistics and Probability

Cite this

Granger causality analysis with nonuniform sampling and its application to pulse-coupled nonlinear dynamics. / Zhang, Yaoyu; Xiao, Yanyang; Zhou, Doug; Cai, David.

In: Physical Review E, Vol. 93, No. 4, 042217, 26.04.2016.

Research output: Contribution to journalArticle

@article{f22977d5cabc4719a2232b83a2d981b4,
title = "Granger causality analysis with nonuniform sampling and its application to pulse-coupled nonlinear dynamics",
abstract = "The Granger causality (GC) analysis is an effective approach to infer causal relations for time series. However, for data obtained by uniform sampling (i.e., with an equal sampling time interval), it is known that GC can yield unreliable causal inference due to aliasing if the sampling rate is not sufficiently high. To solve this unreliability issue, we consider the nonuniform sampling scheme as it can mitigate against aliasing. By developing an unbiased estimation of power spectral density of nonuniformly sampled time series, we establish a framework of spectrum-based nonparametric GC analysis. Applying this framework to a general class of pulse-coupled nonlinear networks and utilizing some particular spectral structure possessed by these nonlinear network data, we demonstrate that, for such nonlinear networks with nonuniformly sampled data, reliable GC inference can be achieved at a low nonuniform mean sampling rate at which the traditional uniform sampling GC may lead to spurious causal inference.",
author = "Yaoyu Zhang and Yanyang Xiao and Doug Zhou and David Cai",
year = "2016",
month = "4",
day = "26",
doi = "10.1103/PhysRevE.93.042217",
language = "English (US)",
volume = "93",
journal = "Physical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics",
issn = "1063-651X",
publisher = "American Physical Society",
number = "4",

}

TY - JOUR

T1 - Granger causality analysis with nonuniform sampling and its application to pulse-coupled nonlinear dynamics

AU - Zhang, Yaoyu

AU - Xiao, Yanyang

AU - Zhou, Doug

AU - Cai, David

PY - 2016/4/26

Y1 - 2016/4/26

N2 - The Granger causality (GC) analysis is an effective approach to infer causal relations for time series. However, for data obtained by uniform sampling (i.e., with an equal sampling time interval), it is known that GC can yield unreliable causal inference due to aliasing if the sampling rate is not sufficiently high. To solve this unreliability issue, we consider the nonuniform sampling scheme as it can mitigate against aliasing. By developing an unbiased estimation of power spectral density of nonuniformly sampled time series, we establish a framework of spectrum-based nonparametric GC analysis. Applying this framework to a general class of pulse-coupled nonlinear networks and utilizing some particular spectral structure possessed by these nonlinear network data, we demonstrate that, for such nonlinear networks with nonuniformly sampled data, reliable GC inference can be achieved at a low nonuniform mean sampling rate at which the traditional uniform sampling GC may lead to spurious causal inference.

AB - The Granger causality (GC) analysis is an effective approach to infer causal relations for time series. However, for data obtained by uniform sampling (i.e., with an equal sampling time interval), it is known that GC can yield unreliable causal inference due to aliasing if the sampling rate is not sufficiently high. To solve this unreliability issue, we consider the nonuniform sampling scheme as it can mitigate against aliasing. By developing an unbiased estimation of power spectral density of nonuniformly sampled time series, we establish a framework of spectrum-based nonparametric GC analysis. Applying this framework to a general class of pulse-coupled nonlinear networks and utilizing some particular spectral structure possessed by these nonlinear network data, we demonstrate that, for such nonlinear networks with nonuniformly sampled data, reliable GC inference can be achieved at a low nonuniform mean sampling rate at which the traditional uniform sampling GC may lead to spurious causal inference.

UR - http://www.scopus.com/inward/record.url?scp=84964789473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964789473&partnerID=8YFLogxK

U2 - 10.1103/PhysRevE.93.042217

DO - 10.1103/PhysRevE.93.042217

M3 - Article

VL - 93

JO - Physical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics

JF - Physical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics

SN - 1063-651X

IS - 4

M1 - 042217

ER -