Robust Non-linear Wiener-Granger Causality For Large High-dimensional Data
(English)Manuscript (preprint) (Other academic)
Wiener-Granger causality is a widely used framework of causal analysis for temporally resolved events. We introduce a new measure of Wiener-Granger causality based on kernelization of partial canonical correlation analysis with specific advantages in the context of large high-dimensional data. The introduced measure is able to detect non-linear and non-monotonous signals, is designed to be immune to noise, and offers tunability in terms of computational complexity in its estimations. Furthermore, we show that, under specified conditions, the intro- duced measure can be regarded as an estimate of conditional mutual information (tranfer entropy). The functionality of this measure is assessed using comparative simulations where it outperforms other existing methods. The paper is concluded with an application to climatological data.
Probability Theory and Statistics
Research subject Mathematical Statistics
IdentifiersURN: urn:nbn:se:su:diva-101590OAI: oai:DiVA.org:su-101590DiVA: diva2:704415
FunderEU, FP7, Seventh Framework ProgrammeSwedish Research Council