FRM Part II · FRM Exam Part II · Non-parametric Approaches
A bank switches from equally weighted historical simulation to the age-weighted (BRW) approach with decay factor lambda = 0.98. Compared with the equally weighted approach, which outcome is most likely immediately after a sudden jump in market volatility?
VaR rises faster. The age-weighted approach gives recent observations larger weights than older ones, so large losses from a sudden volatility jump move the weighted quantile more quickly than under equal weighting. Weights still sum to one, so VaR remains well defined.
- AVaR rises faster because recent large losses receive greater weightCorrect
- BVaR rises more slowly because older observations are given greater weight
- CVaR is unchanged because weights do not affect quantiles
- DVaR becomes undefined because weights no longer sum to one
Explanation
Age weighting gives more weight to recent observations, so new large losses move the weighted quantile more quickly. Weights are normalized to sum to one, so VaR remains defined. The weights do affect the quantile.
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.
More Non-parametric Approaches questions
- Which statement best describes a limitation or feature of the age-weighted (BRW) historical simulation approach compared with equal-weighted…
- A risk manager compares standard historical simulation with bootstrap historical simulation for a 99% VaR on a portfolio with a short 250-da…
- Which limitation is most characteristic of basic historical simulation VaR at a 99.9% confidence level using two years of daily data?
- An analyst compares a plain historical simulation estimate of VaR with a kernel-smoothed estimate from the same 250-day sample. The data con…
- A risk analyst at a bank has 500 daily P&L observations and wants a confidence interval around the 99% historical simulation VaR. She resamp…
- Which statement about the choice of kernel function and bandwidth in non-parametric density estimation is most accurate?