FRM Part II · FRM Exam Part II · Empirical Properties of Correlation: How Do Correlations Behave in the Real World?
A commodity trader notes that the correlation between crude oil and natural gas futures returns is 0.30 over a long sample, yet in a two-month period of a major supply shock it is 0.80. Which interpretation is most appropriate for risk management?
Correlation changes across regimes, so the 0.30 long-run estimate and the 0.80 shock-period estimate both carry information. Risk managers should keep the long-run value for normal conditions and add stress scenarios using higher correlations rather than discarding either.
- AThe long-run figure is wrong and should be replaced by 0.80 permanently
- BCorrelation is regime dependent, so stress scenarios with higher correlation should supplement the long-run estimateCorrect
- CThe short-period figure is meaningless because correlation cannot exceed 0.50 for commodities
- DCorrelation differences imply that volatilities must also differ, so no action is required
Explanation
Correlation is time varying and rises in stress events. A sound approach keeps the long-run estimate for normal conditions but stress-tests with elevated correlation. Replacing it permanently ignores mean reversion, and there is no 0.50 cap.
Did you get it right without looking?
One question tells you little. A timed set on Empirical Properties of Correlation: How Do Correlations Behave in the Real World? shows your real accuracy, how long you take and where you lose marks.
More Empirical Properties of Correlation: How Do Correlations Behave in the Real World? questions
- An analyst studies daily equity correlations across many stock pairs over several years and plots the distribution of correlation estimates.…
- Empirical research on correlation finds that equity correlations show a specific pattern relative to market direction. Which is best support…
- Equity correlations are estimated in two regimes. A risk manager finds that the average correlation is substantially higher when markets fal…
- A bank's risk team estimates portfolio VaR using correlations measured during a calm period. Empirical research suggests correlations rise i…
- Monthly correlation follows a mean-reverting AR(1) process: rho(t+1) - 0.40 = 0.80 x (rho(t) - 0.40) + noise. The current correlation is 0.6…
- A bank's economic-capital model uses a single average credit-default correlation estimated over a long expansion. Based on empirical evidenc…