Network causality structures among Bitcoin and other financial assets: A directed acyclic graph approach

Abstract

Unlike prior studies that have mostly relied on ad hoc network structures, we use a data-driven methodology, namely the directed acyclic graph (DAG), to uncover the contemporaneous and lagged causal relations among Bitcoin and a set of financial assets. The DAG methodology allows the identification of networks of causality based on the observed correlations and partial correlations approach, without making a priori causal assumptions. The main results indicate that the Bitcoin market is quite isolated, especially during its bull market state. We also conduct forecast error variance decompositions and show that the influence of different financial assets on Bitcoin up to the 20-day horizon does not account for more than 10% of innovations in all cases.