FRM Part II · FRM Exam Part II · Estimating Market Risk Measures: An Introduction and Overview
Two assets each have a one-day 99% normal VaR (zero mean): Asset A USD 4 million and Asset B USD 3 million. The return correlation is 0.5. What is the one-day 99% VaR of the combined portfolio, and how does it compare with the sum of stand-alone VaRs?
With normal returns, VaRs combine like volatilities: the square root of 16 plus 9 plus 2 times 0.5 times 4 times 3 equals the square root of 37, about USD 6.08 million. This is below the USD 7 million sum because correlation is less than one, reflecting diversification.
- AAbout USD 6.08 million, below the USD 7 million sumCorrect
- BAbout USD 5.00 million, below the USD 7 million sum
- CAbout USD 7.00 million, equal to the sum
- DAbout USD 6.08 million, above the USD 7 million sum
Explanation
Portfolio VaR = sqrt(4^2 + 3^2 + 2*0.5*4*3) = sqrt(16+9+12) = sqrt(37) = 6.08 million. Check: that is below 7, showing diversification benefit. 5.00 corresponds to zero correlation. 7.00 corresponds to perfect correlation.
Did you get it right without looking?
One question tells you little. A timed set on Estimating Market Risk Measures: An Introduction and Overview shows your real accuracy, how long you take and where you lose marks.
More Estimating Market Risk Measures: An Introduction and Overview questions
- A portfolio has 200 daily historical P&L observations. The five worst losses (in USD thousands) are 410, 350, 320, 290 and 260, and the sixt…
- An analyst computes a VaR from a large sample using the order-statistic approach. The estimated VaR is USD 4.00 million and its standard err…
- A risk analyst scales a one-day 99% normal VaR of USD 3 million to a 10-day horizon, assuming iid zero-mean normal returns. Which result is …
- A risk manager builds a QQ plot of a loss sample against a normal distribution and sees the points forming an S-shaped curve that is flatter…
- A risk manager considers raising the VaR confidence level from 95% to 99% while keeping the holding period and the normal-distribution model…
- A risk analyst estimates the 95% VaR of a trading portfolio using historical simulation and wants to judge how precise the estimate is. Hold…