Skip to content

FRM Part II · FRM Exam Part II · Case Study: Model Risk and Model Validation

A bank estimates a model's 99% one-day VaR as USD 4.0 million. Validation finds that, across plausible alternative specifications, VaR ranges from USD 3.2 million to USD 5.2 million. Management decides to hold a conservative model-risk buffer so that reported VaR equals the top of the range, and it also wants to know the buffer as a percentage of the base VaR. What is the buffer?

The buffer is USD 1.2 million, which is 30% of base VaR. Raising VaR from 4.0 million to the top of the range at 5.2 million adds 1.2 million, and dividing by the base of 4.0 million gives 30%.

  1. AUSD 0.8 million, or 20% of base VaR
  2. BUSD 1.2 million, or 30% of base VaRCorrect
  3. CUSD 1.2 million, or 23% of base VaR
  4. DUSD 2.0 million, or 50% of base VaR

Explanation

Reported VaR equals 5.2 million; the buffer is 5.2 - 4.0 = 1.2 million. As a share of the base 4.0 it is 30%. The 0.8 million option is the gap to the bottom of the range, in the wrong direction. The 23% option divides by the upper value 5.2 instead of the base VaR, and the 2.0 million option uses the full range width.

Did you get it right without looking?

One question tells you little. A timed set on Case Study: Model Risk and Model Validation shows your real accuracy, how long you take and where you lose marks.

Practise Case Study: Model Risk and Model ValidationFree diagnostic mock

More Case Study: Model Risk and Model Validation questions