Local-maximum-based tail index estimator*

被引：0
作者：
Marijus Vaičiulis
机构：
[1] Vilnius University,Faculty of Mathematics and Informatics
[2] Vilnius University,Institute of Mathematics and Informatics
来源：
Lithuanian Mathematical Journal | 2014年 / 54卷
关键词：
asymptotic normality; extreme value index; generalized DPR estimator; mean squared error; tail index;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In the paper, we continue the investigation of the tail index estimators that are based on maxima over blocks of data and were proposed in [V. Paulauskas, A new estimator for tail index, Acta Appl. Math.,79:55–67, 2003; V. Paulauskas and M. Vaičiulis, Several modifications of DPR estimator of the tail index, Lith. Math. J., 51:36–50, 2011; V. Paulauskas and M. Vaičiulis, Estimation of the tail index in the max-aggregation scheme, Lith. Math. J., 52:297–315, 2012]. We construct a new tail index estimator based on local maxima and prove the weak consistency and asymptotic normality of this new estimator in the case of i.i.d. observations. We also prove the weak consistency in the case where data are generated by a nonstationary max-MA(q) process. Monte Carlo simulations show that our estimator is competitive with some popular estimators.
引用
收藏
页码：503 / 526
页数：23
相关论文
共 38 条
[1]  
Fraga Alves MI(2003)A new class of semiparametric estimators of the second order parameter Port. Math. 60 193-213
[2]  
Gomes MI(1978)Two central limit problems for dependent random variables Z. Wahrscheinlichkeitstheor. Verw. Geb. 43 223-243
[3]  
de Haan L(1989)Basic properties and prediction of Max-ARMA processes Adv. Appl. Probab. 21 781-803
[4]  
Chen LHY(2000)More on J. Theor. Probab. 13 39-64
[5]  
Davis RA(1998)-stable convex sets in Banach spaces Stat. Neerl. 52 60-70
[6]  
Resnick SI(1993)Comparison of tail index estimators J. Multivariate Anal. 47 173-195
[7]  
Davydov Y(1988)Optimal choice of sample fraction in extreme-value estimation Stochastic Processes Appl. 75 149-172
[8]  
Paulauskas V(2008)Selecting the optimal sample fraction in univariate extreme value estimation Extremes 11 3-34
[9]  
Račkauskas A(2001)e Castro, M.I. Fraga Alves, and D. Pestana, Statistics of extremes for iid data and breakthroughs in the estimation of the extreme value index: Laurens de Haan leading contributions J. Stat. Plann. Inference 93 161-180
[10]  
De Haan L(2002)Generalizations of the Hill estimator – asymptotic versus finite sample behavior Extremes 5 5-31
1234