Skip to content

FRM Part II · FRM Exam Part II · Financial Correlation Modeling - Bottom-Up Approaches

A bank's analyst estimates the correlation of daily returns between two assets using a rolling window and finds that correlation is much higher on days when both markets fall sharply than on days when both rise sharply by the same magnitude. Which conclusion is best supported?

Correlation is asymmetric, with stronger dependence in down markets. A constant-correlation Gaussian model cannot capture this lower-tail dependence, so it understates the likelihood of joint large losses and the portfolio's downside risk.

  1. ACorrelation is asymmetric, with stronger dependence in down markets, so a single constant-correlation Gaussian model understates joint downside riskCorrect
  2. BCorrelation is symmetric, so a Gaussian copula is adequate for tail risk
  3. CThe data show correlation is negatively related to volatility
  4. DThe data show that correlation is stable and unaffected by market direction

Explanation

Higher dependence in joint downturns than upturns is asymmetric (lower-tail) dependence. A Gaussian copula with constant correlation has no such asymmetry and so understates joint losses. The other options contradict the observation.

Did you get it right without looking?

One question tells you little. A timed set on Financial Correlation Modeling - Bottom-Up Approaches shows your real accuracy, how long you take and where you lose marks.

Practise Financial Correlation Modeling - Bottom-Up ApproachesFree diagnostic mock

More Financial Correlation Modeling - Bottom-Up Approaches questions