*
* Example 7.5 from page 300
*
open data d-ibmln98.dat
data(format=free,org=columns) 1 9190 ibmlog
set ibmlog = .01*ibmlog
*
* This produces slightly different results than shown because RATS determines the
* quantiles by taking 1+p(n-1), not pn. While this is only makes a slight
* difference for large n, the formula used by RATS gives the "correct" empirical
* values for small n.
*
* The %FRACTILES function returns a 2 vector in this case, with the .05 and .01
* quantiles respectively.
*
compute fr=%fractiles(ibmlog,||.05,.01||)
disp "5% VaR on 10000000, Empirical" -fr(1)*10000000
disp "1% VaR on 10000000, Empirical" -fr(2)*10000000