Skip to content

FRM Part II · FRM Exam Part II · Portfolio Performance Evaluation

An analyst runs a returns-based style analysis for a fund using 36 months of data. Results show unstable weights: the small-cap weight swings from 5% to 40% between rolling windows, and two style indices have a correlation of 0.95. Which is the most appropriate conclusion and action?

Multicollinearity between highly correlated style indices is the likely cause of the unstable weights. The better response is to use fewer, less correlated indices or a longer window and cross-check with holdings, rather than conclude style drift or alpha from noisy estimates.

  1. AThe fund is clearly style drifting; the manager should be terminated
  2. BMulticollinearity among the style indices is likely distorting the estimates; use fewer, less correlated indices or a longer windowCorrect
  3. CThe R-squared must be negative; the regression is invalid
  4. DThe instability proves the fund has high alpha

Explanation

Highly correlated explanatory indices make regression weights imprecise and unstable (multicollinearity), so swings may be estimation noise rather than true drift. Remedies include choosing distinct, low-correlation style indices and using more observations, then cross-checking with holdings data. R-squared from a constrained regression is not negative, and instability says nothing about alpha.

Did you get it right without looking?

One question tells you little. A timed set on Portfolio Performance Evaluation shows your real accuracy, how long you take and where you lose marks.

Practise Portfolio Performance EvaluationFree diagnostic mock

More Portfolio Performance Evaluation questions