FRM Part I · FRM Exam Part I · Measuring and Monitoring Volatility
Using EWMA with λ = 0.94 for all terms, prior variances are 0.0001 for X (1% volatility) and 0.0004 for Y (2% volatility), and the prior covariance is 0.00012 (correlation 0.60). Today X returns +2% and Y returns -1%. What is the updated correlation, to two decimals?
The updated correlation is about 0.47. After the EWMA update, the variances are 0.000118 and 0.000382 and the covariance is 0.0001008. Dividing the covariance by the square root of the variance product gives roughly 0.47, down from 0.60, because today's returns moved in opposite directions.
- A0.47Correct
- B0.50
- C0.59
- D0.60
Explanation
Var X = 0.94×0.0001 + 0.06×0.0004 = 0.000118. Var Y = 0.94×0.0004 + 0.06×0.0001 = 0.000382. Cov = 0.94×0.00012 + 0.06×(-0.0002) = 0.0001008. Correlation = 0.0001008 / sqrt(0.000118×0.000382) = 0.0001008/0.0002123 ≈ 0.47. Dividing by the old volatilities (0.0002) gives 0.50, which is wrong because the variances also update.
Did you get it right without looking?
One question tells you little. A timed set on Measuring and Monitoring Volatility shows your real accuracy, how long you take and where you lose marks.
More Measuring and Monitoring Volatility questions
- Using EWMA with lambda = 0.97, the prior-day variance of Asset A is 0.000400, of Asset B is 0.000900, and the prior-day covariance is 0.0002…
- A risk manager builds an EWMA covariance matrix for many risk factors. Which design choice ensures the resulting matrix is positive semi-def…
- After fitting a GARCH(1,1) model, an analyst wants to test whether it captures volatility clustering. Which diagnostic is most appropriate?
- An analyst notes that over several years, implied volatility from index options has on average been higher than the subsequently realized vo…
- In the EWMA model, which statement about the decay factor lambda is correct?
- After fitting a GARCH(1,1) model, an analyst wants to check whether it adequately captures volatility clustering. Which diagnostic is most a…