Smoothing the Hill Estimator

Advances in Applied Probability - Tập 29 Số 1 - Trang 271-293 - 1997
Sidney I. Resnick1, Cătălin Stărică1
1(Cornell University

Tóm tắt

For sequences of i.i.d. random variables whose common tail 1 –Fis regularly varying at infinity wtih an unknown index –α< 0, it is well known that the Hill estimator is consistent for α–1and usually asymptotically normally distributed. However, because the Hill estimator is a function ofk = k(n), the number of upper order statistics used and which is only subject to the conditionsk→∞,k/n →0, its use in practice is problematic since there are few reliable guidelines about how to choosek.The purpose of this paper is to make the use of the Hill estimator more reliable through an averaging technique which reduces the asymptotic variance. As a direct result the range in which the smoothed estimator varies as a function ofkdecreases and the successful use of the esimator is made less dependent on the choice ofk.A tail empirical process approach is used to prove the weak convergence of a process closely related to the Hill estimator. The smoothed version of the Hill estimator is a functional of the tail empirical process.

Từ khóa


Tài liệu tham khảo

10.1007/BF00532510

10.21236/ADA223472

10.1017/S0021900200102621

10.1007/978-0-387-75953-1

Mason, 1988, A strong invariance theorem for the tail empirical process, Ann. Inst. Henri Poincaré, 24, 491

10.1214/aop/1176993783

10.1080/15326349608807407

10.1214/aos/1176349551

10.1016/0047-259X(90)90080-2

10.1080/15326349308807267

10.1007/BF01046994

10.1214/aos/1176349656

Billingsley, 1968, Convergence of Probability Measures.

Mason, 1994, Weak Convergence of the Hill Estimator Process in Extreme Value Theory and Applications.

10.1214/aos/1176343247

Haan L. De and Peng L. (1995) Comparison of tail index estimators. Preprint.

10.1080/15326349508807362

Haan L. De and Stadtmüller U. (1994) Generalized regular variation of second order. Preprint.

Hall, 1982, On some simple estimates of an exponent of regular variation, J. R. Statist. Soc., B 44, 37, 10.1111/j.2517-6161.1982.tb01183.x

10.1016/0304-4149(92)90137-F

10.1093/qmath/38.1.45

10.1214/aos/1176346596

Geluk J. , Haan L. De , Resnick S. and Starica C. (1995) Second order regular variation, convolution and the central limit theorem. Preprint.

10.1214/aos/1176348261

10.1017/CBO9780511721434

Geluk, 1987, CWI Tract 40

Dekkers, 1991, Thesis.

10.1017/S0305004100063751

Thông tin
Thông tin xuất bản

Advances in Applied Probability

Tập 29 Số 1

271-293

Thông tin tác giả