Skip to content

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

During ongoing monitoring, a bank finds that the population stability index for a key input variable of its probability-of-default model has risen well above the internal threshold, though discriminatory power is still unchanged. What does this most likely indicate?

It indicates the input population has drifted from the development data, so the model may be operating outside its intended range and needs review and calibration testing. It is an early warning, not proof of failure, and intact rank-ordering does not remove the need for backtesting.

  1. AThe model has been proven to be inaccurate
  2. BThe input population has shifted from development data, so the model may be used outside its intended range and needs reviewCorrect
  3. CThe model is overfitted and should be retired immediately
  4. DBacktesting is unnecessary because rank-ordering remains intact

Explanation

A high PSI signals the input distribution has drifted from the development sample, an early warning that calibration or assumptions may no longer hold. Unchanged discrimination does not guarantee calibration remains accurate, so escalation and review are warranted rather than immediate retirement or dismissal of backtesting.

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