Estimating the expected shortfall of cryptocurrencies: An evaluation based on backtesting

Abstract

We estimate the Expected Shortfall (ES) of four major cryptocurrencies using various error distributions and GARCH-type models for conditional variance. Our aim is to examine which distributions perform better and to check what component of the specification plays a more important role in estimating ES. We evaluate the performance of the estimations using a rolling-window backtesting technique. Our results highlight the importance of estimating the ES of Bitcoin using a generalized GARCH model and a non-normal error distribution with at least two parameters. Though the results for other cryptocurrencies are less clear-cut, heavy-tailed distributions continue to outperform the normal distribution.