Skip to content

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

A bank's VaR model has a validated model risk add-on. A validator argues for increasing the add-on after finding that the model's parameters were estimated over a calm period only. Which type of model risk does this finding most directly illustrate?

It illustrates calibration or estimation risk. Parameters fitted only to a calm period do not represent stressed conditions, so tail risk is likely understated. The issue lies in unrepresentative data, not in coding mistakes, user misuse or documentation.

  1. AImplementation error in the code
  2. BCalibration/estimation risk from unrepresentative dataCorrect
  3. CMisuse of model output by business users
  4. DModel risk from inadequate documentation

Explanation

Parameters estimated on a calm sample may understate volatility and tail behaviour in stress; this is a data and calibration weakness. It is not a coding error or a usage problem, as the model works as designed but is fed unrepresentative inputs.

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