Institute Homepage DE Sign In

Back

Empirical Inference Conference Paper 2008

Assessing Nonlinear Granger Causality from Multivariate Time Series

no image
Empirical Inference
Xiaohai Sun

A straightforward nonlinear extension of Granger’s concept of causality in the kernel framework is suggested. The kernel-based approach to assessing nonlinear Granger causality in multivariate time series enables us to determine, in a model-free way, whether the causal relation between two time series is present or not and whether it is direct or mediated by other processes. The trace norm of the so-called covariance operator in feature space is used to measure the prediction error. Relying on this measure, we test the improvement of predictability between time series by subsampling-based multiple testing. The distributional properties of the resulting p-values reveal the direction of Granger causality. Experiments with simulated and real-world data show that our method provides encouraging results.

Author(s): Sun, X.
Journal: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2008
Pages: 440-455
Year: 2008
Month: September
Day: 0
Editors: Daelemans, W. , B. Goethals, K. Morik
Publisher: Springer
Bibtex Type: Conference Paper (inproceedings)
Address: Berlin, Germany
DOI: 10.1007/978-3-540-87481-2_29
Event Name: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2008)
Event Place: Antwerpen, Belgium
Digital: 0
Electronic Archiving: grant_archive
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik
Links:

BibTex 

@inproceedings{5254,
  title = {Assessing Nonlinear Granger Causality from Multivariate Time Series},
  journal = {Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2008},
  abstract = {A straightforward nonlinear extension of Granger’s concept of causality in the kernel framework is suggested. The kernel-based approach to assessing nonlinear Granger causality in multivariate time series enables us to determine, in a model-free way, whether the causal relation between two time series is present or not and whether it is direct or mediated by other processes. The trace norm of the so-called covariance operator in feature space is used to measure the prediction error. Relying on this measure, we test the improvement of predictability between time series by subsampling-based multiple testing. The distributional properties of the resulting p-values reveal the direction of Granger causality. Experiments with simulated and real-world data show that our method provides encouraging results.},
  pages = {440-455},
  editors = {Daelemans, W. , B. Goethals, K. Morik},
  publisher = {Springer},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Berlin, Germany},
  month = sep,
  year = {2008},
  slug = {5254},
  author = {Sun, X.},
  month_numeric = {9}
}