Skip to content

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

A bank's VaR model is validated separately by three teams. Team A confirms the formulas are correct. Team B confirms the spreadsheet matches the formulas. Team C finds the model was calibrated on 250 days of data with no stress period, then used to set limits in a volatile market. Which conclusion best reflects model risk principles?

Sound formulas and correct code do not eliminate model risk. The calibration window lacked stress, so VaR may understate risk in volatile markets. The limit-setting use therefore needs effective challenge, such as a stressed calibration or conservative adjustments.

  1. ACorrect formulas and code do not remove risk from calibration data and use, so the model's limit-setting role needs challenge and compensating adjustmentsCorrect
  2. BThe model is fully validated because two of three teams found no errors
  3. CModel risk exists only where code differs from formulas, so no action is needed
  4. DThe risk is eliminated by raising the confidence level alone

Explanation

Model risk arises across design, data, implementation and use. Passing the first two checks does not address the unrepresentative calibration window, which can understate risk in volatile markets. Majority voting among validation teams is not a valid standard, and changing the confidence level does not fix the data problem.

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