Skip to content

FRM Part II · FRM Exam Part II · Validating Bank Holding Companies' Value-at-Risk Models for Market Risk

A validator notes that a bank's 99% VaR model passes the Kupiec test with a 1% exception rate, but a low-power concern is raised. Which factor most directly causes backtests of 99% VaR to have low power to reject a flawed model?

Backtests of 99% VaR have low power because exceptions are rare: only about 2 or 3 are expected in a year of data. With so few observations, it is hard to statistically distinguish a correct model from a moderately inaccurate one.

  1. AExceptions at 99% confidence are rare, so a limited sample yields few observations to distinguish modelsCorrect
  2. BVaR is always computed using historical simulation
  3. CThe chi-square distribution cannot be used for likelihood ratio tests
  4. DDaily P&L data is always autocorrelated

Explanation

At 99% confidence only about 2.5 exceptions are expected in 250 days, so a small sample cannot reliably distinguish a correct model from a moderately wrong one. Longer samples or lower confidence levels raise power. The other options state incorrect or unrelated claims.

Did you get it right without looking?

One question tells you little. A timed set on Validating Bank Holding Companies' Value-at-Risk Models for Market Risk shows your real accuracy, how long you take and where you lose marks.

Practise Validating Bank Holding Companies' Value-at-Risk Models for Market RiskFree diagnostic mock

More Validating Bank Holding Companies' Value-at-Risk Models for Market Risk questions