Skip to content

FRM Part I · FRM Exam Part I · Measuring Return, Volatility, and Correlation

During a market crisis, a risk manager observes that the correlation between two equity indices computed using only days with large absolute returns is much higher than the full-sample correlation. What is the most appropriate interpretation?

Correlation is unstable and tends to rise in stressed markets, so a single full-sample estimate can understate the loss of diversification in a crisis. Risk managers should consider stressed or conditional correlations rather than assuming constant dependence.

  1. ACorrelations are constant over time, so the full-sample figure is a biased estimate
  2. BCorrelation is unstable and tends to rise in stressed markets, so a single unconditional estimate may understate diversification loss in crisesCorrect
  3. CThe result shows the indices are independent in normal times and perfectly dependent in crises
  4. DThe higher correlation is entirely a sampling artifact and should be ignored

Explanation

Correlation is not stable; it often increases in stressed, high-volatility periods. Relying on the unconditional correlation can understate joint tail losses. Conditioning on large moves also introduces some bias, but the pattern of correlation breakdown is a recognized pitfall.

Did you get it right without looking?

One question tells you little. A timed set on Measuring Return, Volatility, and Correlation shows your real accuracy, how long you take and where you lose marks.

Practise Measuring Return, Volatility, and CorrelationFree diagnostic mock

More Measuring Return, Volatility, and Correlation questions