Just looked again at the what I did on the Swiss FX shock, looking at how the various risk measures performed in the days after the event, and also looking at the risk of the inverse FX.
The original analysis just looked at the risk of the Franc appreciating, but why not look at the risk of the euro appreciating. Starting with the Franc to Euro
and the inverse
It shows just how badly the t-GARCH performs, no surprise, it certainly needs more than 1000 days used here for the estimation. HS and EVT hardly budge, and GARCH recovers faster than EWMA.
Also, it is interesting that the symmetric methods see the risk the same way, regardless of appreciation or depreciation. That of course falls out of the model structure, but it doesn’t make that much economic sense.
© All rights reserved, Jon Danielsson, 2018