A robust hybrid method using dynamic network analysis and Weighted Mahalanobis distance for modeling systemic risk in the international energy market

Abstract

This paper proposes a novel hybrid method called Weighted Turbulence, which combines the dynamic network and weighted Mahalanobis distance to measure the overall systemic risk level of the international energy markets system. We simultaneously capture two essential drivers of systemic risk on international energy markets, including the abnormal price behavior of the single market and the interconnectedness among different energy markets, as the fundamental points of our modeling. It makes our proposed model can characterize the larger influential level of the abnormal behavior of the core energy market than that of the periphery markets on the systemic risk level and eliminate the negative impact of the non-systematic markets of the targeted markets system on the systemic risk measuring, which few existing schemes can achieve that. The empirical study further confirms the effectiveness and robustness of our proposed model. It can accurately detect the spikes of systemic risk in international energy markets, and the measuring results are unaffected by the interference of the noise data. The proposed method is applicable in practical systemic risk measurement, which has valuable theoretical and practical implications for related energy market participants.