Empirical Inference

A Kernel Test of Nonlinear Granger Causality

2008

Conference Paper

ei


We present a novel test of nonlinear Granger causality in bivariate time series. The trace norm of conditional covariance operators is used to capture the prediction errors. Based on this measure, a subsampling-based multiple testing procedure tests the prediction improvement of one time series by the other one. The distributional properties of the resulting p-values reveal the direction of Granger causality. Encouraging results of experiments with simulated and real-world data support our approach.

Author(s): Sun, X.
Journal: Proceedings of the Workshop on Inference and Estimation in Probabilistic Time-Series Models
Pages: 79-89
Year: 2008
Month: June
Day: 0
Editors: Barber, D. , A. T. Cemgil, S. Chiappa
Publisher: Isaac Newton Institute for Mathematical Sciences

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: Workshop on Inference and Estimation in Probabilistic Time-Series Models
Event Place: Cambridge, UK

Address: Cambridge, United Kingdom
Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF

BibTex

@inproceedings{5252,
  title = {A Kernel Test of Nonlinear Granger Causality},
  author = {Sun, X.},
  journal = {Proceedings of the Workshop on Inference and Estimation in Probabilistic Time-Series Models},
  pages = {79-89},
  editors = {Barber, D. , A. T. Cemgil, S. Chiappa},
  publisher = {Isaac Newton Institute for Mathematical Sciences},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Cambridge, United Kingdom},
  month = jun,
  year = {2008},
  doi = {},
  month_numeric = {6}
}