Ekonomi & Bisnis editorial
Open AccessOA2023
Linear and Nonlinear Causality in Financial Markets
This study introduces a framework using transfer entropy and convergent cross-mapping with Fourier surrogates to disentangle linear and nonlinear causality in financial markets. Applied to German and U.S. stock indices, it finds significant nonlinear causality, showing that correlation underestimates causality and motivating applications in trading and risk management.
Haochun Ma; Davide Prosperino; Alexander Haluszczynski; C. Räth· Chaos· 2023· DOI 10.1063/5.0184267
The core problem
Identifying and quantifying co-dependence between financial instruments is a key challenge for researchers and practitioners in the financial industry. Linear measures such as the Pearson correlation are still widely used today, although their limited explanatory power is well known. In this paper, we present a much more general framework for assessing co-dependencies by identifying linear and nonlinear causalities in the complex system of financial markets. To do so, we use two different causal inference methods, transfer entropy and convergent cross-mapping, and employ Fourier transform surrogates to separate their linear and nonlinear contributions. We find that stock indices in Germany and the U.S. exhibit a significant degree of nonlinear causality and that correlation, while a very good proxy for linear causality, disregards nonlinear effects and hence underestimates causality itself. The presented framework enables the measurement of nonlinear causality, the correlation-causality fallacy, and motivates how causality can be used for inferring market signals, pair trading, and risk management of portfolios. Our results suggest that linear and nonlinear causality can be used as early warning indicators of abnormal market behavior, allowing for better trading strategies and risk management.
Innovation
The authors employ two causal inference methods: transfer entropy and convergent cross-mapping. Transfer entropy, a model-free measure based on information theory, quantifies the amount of directed information transfer between two time series. Convergent cross-mapping, rooted in dynamical systems theory, detects causality by reconstructing the state space of one variable from the other. To separate linear and nonlinear contributions, Fourier transform surrogates are used. These surrogates preserve the linear properties (e.g., power spectrum and autocorrelation) of the original data while destroying nonlinear dependencies. By comparing causality measures computed on the original data with those on surrogates, the authors can attribute causality to linear or nonlinear sources. The framework is applied to stock indices in Germany and the U.S., though specific indices and time periods are not detailed in the abstract. The methodology allows for a robust decomposition of causality into linear and nonlinear components, providing a more nuanced understanding of market co-dependencies.
Introduction
Identifying and quantifying co-dependence between financial instruments is a key challenge for researchers and practitioners in the financial industry. Linear measures such as the Pearson correlation are still widely used today, although their limited explanatory power is well known. In this paper, we present a much more general framework for assessing co-dependencies by identifying linear and nonlinear causalities in the complex system of financial markets. To do so, we use two different causal inference methods, transfer entropy and convergent cross-mapping, and employ Fourier transform surrogates to separate their linear and nonlinear contributions. We find that stock indices in Germany and the U.S. exhibit a significant degree of nonlinear causality and that correlation, while a very good proxy for linear causality, disregards nonlinear effects and hence underestimates causality itself. The presented framework enables the measurement of nonlinear causality, the correlation-causality fallacy, and motivates how causality can be used for inferring market signals, pair trading, and risk management of portfolios. Our results suggest that linear and nonlinear causality can be used as early warning indicators of abnormal market behavior, allowing for better trading strategies and risk management.
Why it matters
The presented framework enables the measurement of nonlinear causality and highlights the correlation-causality fallacy—the mistaken assumption that correlation implies causation. The authors motivate how causality can be used for inferring market signals, pair trading, and risk management of portfolios. By identifying both linear and nonlinear causal links, traders and risk managers can better anticipate market movements and design more effective strategies. The use of causality as early warning indicators of abnormal market behavior is proposed, allowing for proactive measures. The study contributes to the literature by providing a general framework that goes beyond linear measures and by demonstrating the importance of nonlinear causality in financial markets. The findings have implications for portfolio diversification, hedging, and systemic risk assessment. Future research could extend the framework to other asset classes and higher-frequency data.
Who should read this
Pembaca Research Digest dan praktisi rumpun ini.
Opening member content…