Not really on topic for the list, but try comparing the normal VaR with a
VaR calculated from a Stable Distribution (check to see your returns data
is actually a better fit with the stable...in most equity returns, it
almost certainly will be).
You will find the 90 / 95th confidence levels to be quite similar but the
99th drastically different. This is even more so when calculating Expected
Shortfall.
On Tue, Sep 4, 2012 at 6:20 AM, Christofer Bogaso <
bogaso.christofer@gmail.com> wrote:
> Dear all, I am preparing a presentation to demonstate why
> Value-at-Risk (VaR) is not a good measure for Risk. Basically, my
> intention is to show that: For 2 drastically different distributions,
> the VaR (i.e. 5th percentiles) can be just same.
>
> Can somebody help me to find such drastically different two
> statistical distributions which have same 5th percentile?
>
> Thanks for your help.
>
> _______________________________________________
> R-SIG-Finance@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions
> should go.
>
[[alternative HTML version deleted]]