Re: Ten-day 99% VaR has worked fine.

From: Krassimir
Affiliation:
Address: kkostadinov@gmx.de
Date: 02 Nov 2006
Time: 11:36:26

Comments

You have two reasonable approaches and get two completely different VaR 99%. You apply the approaches to a number of historic dataset and you get -- guess what -- a number of VaR 99% pairs, with huge differences between the VaR 99% numbers in each pair. You cannot tell which of those is closer to the true one, as you do not know the true one. (One of) the problem(s) with the VaR 99% is that you cannot apply reasonably backtesting to assess model risk...

Disclaimer