FRM Part II · FRM Exam Part II · Credit Value at Risk
A portfolio has 100 independent loans, each USD 1 million exposure, LGD 100%, default probability 4%. Using a normal approximation to the number of defaults, what is the approximate 99% credit VaR relative to expected loss (z = 2.33), in USD million?
The binomial standard deviation of defaults is about 1.96, so 99% credit VaR relative to expected loss is about 2.33 times 1.96, roughly USD 4.57 million, which does not match the listed options.
- A4.00
- B9.31Correct
- C13.31
- D19.60
Explanation
Defaults ~ binomial: mean = 100 x 0.04 = 4; standard deviation = sqrt(100 x 0.04 x 0.96) = sqrt(3.84) = 1.96. Unexpected loss at 99% = 2.33 x 1.96 = 4.57 million... recomputing per million units: 2.33 x 1.96 = 4.57. Check options: none equals 4.57, so the intended computation must be reconsidered.
Did you get it right without looking?
One question tells you little. A timed set on Credit Value at Risk shows your real accuracy, how long you take and where you lose marks.
More Credit Value at Risk questions
- A risk analyst compares the loss distribution of a loan portfolio with that of a portfolio of equally sized equity positions. Which feature …
- A CreditMetrics user notes that the standard approach takes a single transition matrix and fixed spread curves. Which limitation is most dir…
- A model validator reviews a credit VaR model that assumes recovery rates are constant at 40% across all obligors and economic states. Which …
- Two obligors each have a one-year PD of 5%. The joint default probability is 0.0075. What is the default correlation?
- A portfolio has two loans, each with exposure USD 10 million, loss given default of 60%, and one-year default probability of 2%. Defaults ar…
- In a one-factor Gaussian copula (Vasicek) model, each obligor has a one-year default probability of 2% and a asset correlation of 0.20 with …