Skip to content

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

Over a sample, Model A's average quantile score is 2.10 and Model B's is 2.35, with lower being better. The Diebold-Mariano style test on the daily score differences gives a p-value of 0.40. What is the most appropriate conclusion?

Model A has the lower average score, but with a p-value of 0.40 the difference is not statistically significant. Superiority cannot be claimed, and the comparison test says nothing about whether either model is correctly specified.

  1. AModel A has the lower average score, but the difference is not statistically significant, so superiority is not establishedCorrect
  2. BModel B is significantly better because its score is higher
  3. CModel A is proven to be correctly specified
  4. DBoth models must be rejected by the Kupiec test

Explanation

Lower score is better, so A looks better in-sample, but a p-value of 0.40 means the difference could easily arise by chance. The comparison test addresses relative performance, not correct specification, and says nothing about Kupiec rejection. Choosing B confuses the direction of the score.

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