Skip to content

FRM Part II · FRM Exam Part II · Early Warning Indicators

A bank's EWI back-test over 20 historical stress episodes shows that a funding concentration indicator breached its threshold before 15 of the episodes, and it also breached in 30 periods during which no stress followed. Management wants to reduce false alarms without materially reducing the hit rate. Which action is most consistent with sound threshold design?

Management should weigh the 75% hit rate against the false alarms, then recalibrate the threshold or add a confirming indicator and back-test again. Lowering the threshold adds false alarms, and raising it sharply misses stress, so some false signals must be accepted for timely warning.

  1. ALower the threshold so that it is breached more often, which raises sensitivity and removes the false alarms
  2. BRaise the threshold sharply until it is rarely breached, accepting that few stress episodes will be signalled
  3. CAnalyze the trade-off between hit rate (15/20 = 75%) and false alarms, then adjust the threshold or add a confirming indicator, and re-test, accepting some false signals as the cost of timely warningCorrect
  4. DRemove the indicator because any false alarm shows it has no predictive value

Explanation

Threshold setting involves a trade-off between missed signals and false alarms. The hit rate is 15/20 = 75%. Lowering the threshold increases false alarms, and raising it sharply loses timely warnings. Best practice is to recalibrate, possibly combine with a confirming indicator, and re-test, tolerating some false signals.

Did you get it right without looking?

One question tells you little. A timed set on Early Warning Indicators shows your real accuracy, how long you take and where you lose marks.

More Early Warning Indicators questions