Non-linear dependence and Granger causality: A vine copula approach

TL;DR

This paper introduces a vine copula-based Granger causality test for non-linear dependencies in bivariate Markov processes, demonstrating improved statistical properties and applying it to U.S. economic data to reveal bidirectional causality.

Contribution

It presents a novel vine copula approach for Granger causality testing that outperforms previous methods in capturing non-linear dependence structures.

Findings

The new test shows better statistical properties than previous methods.

Applied to U.S. data, it finds bidirectional causality between GDP and energy consumption.

Abstract

Inspired by Jang et al. (2022), we propose a Granger causality-in-the-mean test for bivariate $k-$Markov stationary processes based on a recently introduced class of non-linear models, i.e., vine copula models. By means of a simulation study, we show that the proposed test improves on the statistical properties of the original test in Jang et al. (2022), and also of other previous methods, constituting an excellent tool for testing Granger causality in the presence of non-linear dependence structures. Finally, we apply our test to study the pairwise relationships between energy consumption, GDP and investment in the U.S. and, notably, we find that Granger-causality runs two ways between GDP and energy consumption.