On the asymptotic normality of Hill's estimator
- 1 September 1995
- journal article
- research article
- Published by Cambridge University Press (CUP) in Mathematical Proceedings of the Cambridge Philosophical Society
- Vol. 118 (2) , 375-382
- https://doi.org/10.1017/s0305004100073710
Abstract
LetX,X1,X2, …, be independent random variables with a common distribution functionF(x) =P{X≤x},x∈ℝ, and for eachn∈ℕ, letX1,n≤ … ≤Xn, ndenote the order statistics pertaining to the sampleX1, …,Xn. We assume that 1–F(x) =x−1/cl(x), 0 <x< ∞, wherelis some function slowly varying at infinity andc> 0 is any fixed number. The class of all such distribution functions will be denoted by.This publication has 9 references indexed in Scilit:
- Almost sure convergence of the Hill estimatorMathematical Proceedings of the Cambridge Philosophical Society, 1988
- Regular VariationPublished by Cambridge University Press (CUP) ,1987
- Central limit theorems for sums of extreme valuesMathematical Proceedings of the Cambridge Philosophical Society, 1985
- Kernel Estimates of the Tail Index of a DistributionThe Annals of Statistics, 1985
- On Asymptotic Normality of Hill's Estimator for the Exponent of Regular VariationThe Annals of Statistics, 1985
- Tail Estimates Motivated by Extreme Value TheoryThe Annals of Statistics, 1984
- On Some Simple Estimates of an Exponent of Regular VariationJournal of the Royal Statistical Society Series B: Statistical Methodology, 1982
- Laws of Large Numbers for Sums of Extreme ValuesThe Annals of Probability, 1982
- A Simple General Approach to Inference About the Tail of a DistributionThe Annals of Statistics, 1975