Skip to content

FRM Part II · FRM Exam Part II · Backtesting VaR

A bank's 99% VaR model has produced 4 exceptions in 250 days, which falls in the acceptance region of a backtest. A senior manager concludes the model is proven accurate. Which response best reflects the limitations of backtesting with respect to error types?

Passing a backtest does not prove a model is accurate. At the 99% level exceptions are rare, so samples give low power and a high Type II error probability, meaning flawed models can often go undetected.

  1. AAcceptance does not prove accuracy, because with few observations at the 99% level the Type II error probability can be highCorrect
  2. BAcceptance proves accuracy because Type I error is controlled at the chosen significance level
  3. CThe conclusion is valid because 4 exceptions is below the expected 2.5 only if the model is overstated
  4. DThe conclusion is valid because Type II error is always zero when the null is not rejected

Explanation

Rare 99% exceptions give backtests low power with limited samples, so inaccurate models often pass. Failing to reject is not proof of correctness. Controlling Type I error says nothing about Type II error.

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