Hill estimator
FRM Part 2 glossary · Market Risk
Definition
Tail-index estimator from mean log-exceedances above a threshold; α̂ = 1/ξ̂, sensitive to the exceedance count chosen.
Hill estimator in plain English
The Hill estimator is a tool for measuring how "fat" the tail of a distribution is — meaning how likely truly extreme, rare events (a market crash, a giant loss) really are. You pick a high threshold, look only at the values that blow past it, and average how far past they go (on a log scale); that average tells you the tail-index, a number describing how fast the odds of bigger and bigger events fade out. The catch is that your answer depends heavily on how many of those extreme points you choose to include — too few and it's noisy, too many and you pollute it with ordinary values. Think of judging how dangerous a river is by studying only its biggest floods: exactly which floods you count as "big" changes your verdict.
Learn these first
Practice Hill estimator
The Hill estimator is primarily used to provide a direct estimate of which parameter?
Related FRM Part 2 terms
FRM Part 2 practice questions · FRM Part 2 flashcards · FRM Part 2 study guide