FRM Part II · FRM Exam Part II · Backtesting VaR
A bank's 99% one-day VaR model produced 4 exceptions in 250 days, all in the same two-week period following a market shock. Which conclusion is most appropriate?
The count of 4 is acceptable on a simple frequency test, but clustering of exceptions signals they are not independent, so the model likely adapts slowly to volatility changes. Independence tests or conditional coverage should be applied, and the model deserves review.
- AThe count is acceptable, but clustering suggests exceptions are not independent, so the model may fail to react to changing volatilityCorrect
- BThe model should be accepted because 4 exceptions is above the expected 2.5, which implies VaR is conservative
- CThe model must be rejected because any clustering invalidates the binomial test count
- DThe model is acceptable and clustering is irrelevant because only total exceptions matter
Explanation
4 exceptions is modestly above the 2.5 expected and typically not rejected by a simple count test. However, clustering violates independence, suggesting the model responds slowly to volatility changes. More exceptions than expected means VaR is too low, not conservative.
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.
More Backtesting VaR questions
- A bank's 99% VaR model produces exactly 2.5 exceptions per 250 days on average, matching expectations, so it passes the unconditional covera…
- A risk manager reviews the Basel traffic light backtest for a 99% VaR model using 250 days. She notes that the green zone ends at 4 exceptio…
- A bank's trading desk reports 12 exceptions in 250 days against a 99% one-day VaR. A review finds that 8 of them occurred on days when trade…
- A risk manager backtests a 99% one-day VaR model over 250 days and records exceptions. She applies a test that checks both the number of exc…
- A 99% one-day VaR model is tested over 250 days. If the model is correct, the exception count is approximately binomial with p = 1%. The exp…
- A risk manager finds that a bank's VaR exceptions cluster in consecutive days during volatile periods, while the model uses an equally weigh…