Dependency and causal relationship between ‘Bitcoin’ and financial asset classes: A Bayesian network approach
使用贝叶斯网络和小波相干方法，研究了2011年8月至2021年10月期间比特币波动与多种金融资产（如股票指数、商品指数、债券指数）之间的关系，发现因果关系随市场状态变化，为美国投资者和决策者提供了资产配置与风险管理的启示。
Abstract This study employs the Bayesian Networks (BN) and the wavelet coherence approaches to invest the relationship between Bitcoin volatility and financial asset classes (MSCI world equity index, S&P Goldman Sachs Commodity Index [GSCI], US index and Investment Grade Corporate Bond Index ETF [PIMCO]) using daily data for the period from August 2011 to October 2021. The results show that the causal relationship between Bitcoin and other financial assets varies depending on the market states. During the low volatility periods, Bitcoin has a stronger impact on the GSCI, while during the stability periods, it has a direct effect on the US index and the MSCI world index. In contrast, during high volatility periods, Bitcoin has a direct impact on both the GSCI and PIMCO indices. The key findings enabled us to provide implications for US investors to promote asset allocation and risk management covering both Bitcoin and traditional financial markets. The results suggest that policymakers should watch Botcoin closely to preserve financial stability.