论文信息 - A class of Pickands-type estimators for the extreme value index

A class of Pickands-type estimators for the extreme value index

In this paper we introduce a new class of Pickands-type estimators for the extreme value index. Consistency and asymptotic normality of the estimators are established under suitable regularity conditions. The new estimator uses the same fraction of upper-order statistics as the well-known Pickands estimator, but its asymptotic performance is better by at least 10% if it is chosen in some optimal ways. A simulation study also demonstrates its good finite-sample performance.

Seokhoon Yun | Seokhoon Yun

[1] Michael Falk,et al. Efficiency of convex combinations of pickands estimator of the extreme value index , 1994 .

[2] W. W. Daniel. Applied Nonparametric Statistics , 1979 .

[3] Lionel Weiss,et al. Asymptotic inference about a density function at an end of its range , 1971 .

[4] D. Mason,et al. Central limit theorems for sums of extreme values , 1985, Mathematical Proceedings of the Cambridge Philosophical Society.

[5] L. Haan,et al. On the Estimation of the Extreme-Value Index and Large Quantile Estimation , 1989 .

[6] E. Haeusler,et al. On Asymptotic Normality of Hill's Estimator for the Exponent of Regular Variation , 1985 .

[7] Holger Drees,et al. Refined Pickands estimators of the extreme value index , 1995 .

[8] L. Haan,et al. A moment estimator for the index of an extreme-value distribution , 1989 .

[9] J. Pickands. Statistical Inference Using Extreme Order Statistics , 1975 .

[10] Paul Deheuvels,et al. Almost sure convergence of the Hill estimator , 1988, Mathematical Proceedings of the Cambridge Philosophical Society.

[11] B. M. Hill,et al. A Simple General Approach to Inference About the Tail of a Distribution , 1975 .

[12] D. Mason. Laws of Large Numbers for Sums of Extreme Values , 1982 .