Skip to content

FRM Part II · FRM Exam Part II · Non-parametric Approaches

An analyst compares plain historical simulation VaR with bootstrap historical simulation using the same 250-day dataset of returns. Which statement about the bootstrap's limitation is most accurate?

The bootstrap cannot produce a loss worse than the largest loss in the original data, because it only reuses observed values. It does not extrapolate into the tail or adjust for volatility, and it still assumes the past represents the future.

  1. AIt still cannot produce losses larger than the worst loss in the original sampleCorrect
  2. BIt generates losses beyond the worst observation by extrapolating with a fitted tail distribution
  3. CIt removes dependence on the assumption that past returns are informative about the future
  4. DIt automatically adjusts for current volatility being higher than historical volatility

Explanation

Bootstrap resamples only observed values, so no resampled loss can exceed the worst actual loss. It does not fit a tail model (that is extreme value theory) and it relies on the same assumption that history is representative. It also does not rescale for volatility changes.

Did you get it right without looking?

One question tells you little. A timed set on Non-parametric Approaches shows your real accuracy, how long you take and where you lose marks.

Practise Non-parametric ApproachesFree diagnostic mock

More Non-parametric Approaches questions