Robust Non-linear Wiener-Granger Causality For Large High-dimensional Data

TL;DR

This paper introduces a kernelized Wiener-Granger causality measure tailored for large high-dimensional datasets, capable of detecting non-linear signals and robust to noise, with demonstrated superior performance in simulations and climatological data.

Contribution

A novel non-linear Wiener-Granger causality measure based on kernelized partial canonical correlation analysis, suitable for high-dimensional data and noise immunity.

Findings

Outperforms existing causality detection methods in simulations

Can be interpreted as an estimate of transfer entropy under certain conditions

Successfully applied to climatological data

Abstract

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 introduced measure can be regarded as an estimate of conditional mutual information (transfer 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.