Multi-Layer Spillovers between Volatility and Skewness in International Stock Markets Over a Century of Data: The Role of Disaster Risks

Measuring risk lies at the core of the decision-making process of every financial market participant and monetary authority. However, the bulk of literature treats risk as a function of the second moment (volatility) of the return distribution, based on the implicit unrealistic assumption that asset return are normally distributed. In this paper, we depart from centred moments of distribution by examining risk spillovers involving robust estimates of second and third moments of model-implied distributions of stock returns derived from the quantile autoregressive distributed lag mixed-frequency data sampling (QADL-MIDAS) method. Using a century of data on the stock indices of the G7 and Switzerland over the period May 1917 to February 2023 and applying the multilayer approach to spillovers, we show the following. Firstly, the risk spillover among stock markets is significant within each layer (i.e. volatility and skewness) and across the two layers. Secondly, geopolitical risks have the power to shape both risk layer values, based on an out-of-sample forecasting exercise involving machine-learning methods. Interestingly, the multi-layer approach offers a comprehensive and nuanced view of how risk information is transmitted across major stock markets, while global measures of geopolitical risk affect risk spillovers at shorter horizons up to 6 months, while, at longer horizons, the forecasting exercise is dominated by market-specific characteristics.