FRM Part II · FRM Exam Part II · Validating Bank Holding Companies' Value-at-Risk Models for Market Risk
A bank backtests its one-day 99% VaR model against 250 trading days of hypothetical P&L. Under the Basel traffic-light approach, how many exceptions would the model be expected to produce on average if it is perfectly calibrated?
A perfectly calibrated 99% one-day VaR should be exceeded on 1% of days. Over 250 trading days that gives an expected 2.5 exceptions, found by multiplying 250 by 0.01. This is the benchmark against which observed exception counts are compared.
- A0.25
- B2.5Correct
- C5.0
- D10.0
Explanation
Expected exceptions equal the number of observations times the tail probability: 250 x (1 - 0.99) = 2.5. Choosing 5.0 uses a 98% confidence level, and 0.25 misplaces the decimal point.
Did you get it right without looking?
One question tells you little. A timed set on Validating Bank Holding Companies' Value-at-Risk Models for Market Risk shows your real accuracy, how long you take and where you lose marks.
More Validating Bank Holding Companies' Value-at-Risk Models for Market Risk questions
- A bank's 99% one-day VaR model is backtested over 250 trading days and produces 6 exceptions. Under the Basel traffic-light approach, the nu…
- A bank's 99% one-day VaR model is backtested over 250 trading days and produces 9 exceptions. The validator is deciding how to interpret thi…
- A bank's trading desk shows more exceptions when VaR is compared with actual (clean-plus-dirty) P&L than with hypothetical P&L. Which is the…
- A validator benchmarks a bank's 99% one-day VaR of USD 12.0 million against a vendor model giving USD 15.0 million. Over 250 days, the bank'…
- A bank backtests its 99% one-day VaR over 250 trading days and records 7 exceptions. Under the Basel traffic-light framework, in which zone …
- A bank's validation group finds that backtesting exceptions are clustered in a few consecutive weeks, although the total count of 4 over 250…