Forecasting tail risk for Bitcoin: A dynamic peak over threshold approach

Abstract

This paper employs a dynamic peak over threshold (PoT) model to measure and forecast both the lower and upper tail Value at Risks (VaRs) of Bitcoin returns, which offers a new perspective to investigate the tail risk dynamics for Bitcoin. We evaluate the VaR forecasting accuracy of this model compared with that of the GARCH-EVT models based on Student-t, skewed Student-t and Generalized error distribution. The empirical results illustrate that the dynamic PoT model exhibits superior out-of-sample VaR predictive ability, specifically for the lower tail VaR. Thus, this model can be a useful and reliable alternative for forecasting tail risk.