A0390
Title: Evaluating financial tail risk forecasts with the model confidence set
Authors: Lukas Bauer - University of Freiburg, Statistics and Econometrics (Germany) [presenting]
Abstract: The focus is on the first provision of results on the finite sample properties of the model confidence set (MCS) applied to the asymmetric loss functions specific to financial tail risk forecasts, such as value-at-risk (VaR) and expected shortfall (ES). The emphasis is on statistical loss functions that are strictly consistent. The comprehensive simulation results show that, first, the MCS test keeps the best model more frequently than the confidence level $1-\alpha$ in most settings. Second, it eliminates a few inferior models for out-of-sample sizes of up to four years. Third, the MCS test shows little power against models that underestimate tail risk at the extreme quantile levels p=0.01 and p=0.025, while the power increases with the quantile level p. These findings imply that the MCS test may be suitable to narrow down a set of competing models but that it is not appropriate to test if a new model beats its competitors due to the lack of power.
