Skip to content

FRM Part II · FRM Exam Part II · Backtesting VaR

A risk committee uses an exceptions-based backtest and finds that the 99% VaR model passes, with exceptions within the acceptable range. Which limitation of this result should the committee keep in mind?

An exceptions-based pass shows that the frequency of breaches is plausible, but it ignores how large the losses beyond VaR were. Tail severity therefore remains untested, and the result cannot guarantee future performance or validate specific model assumptions.

  1. APassing guarantees that the model will never be wrong in future periods
  2. BA pass shows the number of exceptions is plausible but does not reveal how large the losses beyond VaR were, so tail severity remains untestedCorrect
  3. CPassing proves that the model's correlation assumptions are correct
  4. DException counts cannot be used to evaluate VaR at all

Explanation

Exception counting only records whether a loss exceeded VaR, not by how much. A model can pass while its tail losses are very large. Also, passing does not guarantee future performance or validate individual assumptions.

Did you get it right without looking?

One question tells you little. A timed set on Backtesting VaR shows your real accuracy, how long you take and where you lose marks.

Practise Backtesting VaRFree diagnostic mock

More Backtesting VaR questions