Skip to content

FRM Part II · FRM Exam Part II · Beyond Exceedance-Based Backtesting of Value-at-Risk Models

A bank has a 99% VaR model that produced zero exceedances in 250 days. Which interpretation is most consistent with the limitations of exceedance-based backtesting?

Zero exceedances against 2.5 expected suggests VaR may be overly conservative, not necessarily accurate. Regulatory-style exceedance tests focus on too many breaches and have low power, so they do little to flag excess conservatism. Further validation using other backtesting methods is warranted.

  1. AThe model is clearly accurate because zero is below the expected count
  2. BThe model may be overly conservative, and exceedance counting alone is weak at identifying this because one-sided tests focus on too many breachesCorrect
  3. CThe model must be rejected because zero exceedances is impossible
  4. DThe model has perfect tail coverage and needs no further validation

Explanation

Expected exceedances are 2.5, so zero suggests VaR may be set too high, tying up excess capital. Regulatory traffic-light style approaches penalize only too many exceedances, and low power means zero is not proof of accuracy. Additional validation is warranted.

Did you get it right without looking?

One question tells you little. A timed set on Beyond Exceedance-Based Backtesting of Value-at-Risk Models shows your real accuracy, how long you take and where you lose marks.

Practise Beyond Exceedance-Based Backtesting of Value-at-Risk ModelsFree diagnostic mock

More Beyond Exceedance-Based Backtesting of Value-at-Risk Models questions