Generalized least-squares estimators for the thickness of heavy tails

被引：18

作者：

Aban, IB ^{[1
]}

Meerschaert, MM ^{[1
]}

机构：

[1] Univ Nevada, Dept Math, Coll Arts & Sci, Reno, NV 89557 USA

来源：

JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 2004年 / 119卷 / 02期

关键词：

least-squares; linear regression; heavy tails; order statistics;

D O I：

10.1016/S0378-3758(02)00419-6

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

For a probability distribution with Power law tails, a log-log transformation makes the tails of the empirical distribution function resemble a straight line, leading to a least-squares estimate of the tail thickness. Taking into account the mean and covariance structure of the extreme order statistics leads to improved tail estimators, and a surprising connection with Hill's estimator. (C) 2002 Elsevier B.V. All rights reserved.

引用

页码：341 / 352

页数：12

共 25 条

[21]

Mandelbrot BB., 1977, FRACTAL GEOMETRY NAT

[22] Measuring tail thickness to estimate the stable index alpha: A critique [J].

McCulloch, JH .

JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 1997, 15 (01) :74-81

[23] A simple robust estimation method for the thickness of heavy tails [J].

Meerschaert, MM ;

Scheffler, HP .

JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1998, 71 (1-2) :19-34

[24] Smoothing the Hill estimator [J].

Resnick, S ;

Starica, C .

ADVANCES IN APPLIED PROBABILITY, 1997, 29 (01) :271-293

[25]

Schultze J., 1996, Statist. Decisions, V14, P353

← 1 2 3 →