PORT Hill and moment estimators for heavy-tailed models

M. Ivette Gomes (1) , M. Isabel Fraga Alves (2) , Paulo Araújo Santos (3)

1 DEIO
2 DEIO
3 Instituto Politécnico de Santarém

In this paper we use the peaks over random threshold (PORT)-methodology, and consider Hill and moment PORT-classes of extreme value index estimators. These estimators are invariant not only to changes in scale, but also to changes in location. The exact performance of the new extreme value index PORT-estimators is compared, through a large-scale Monte-Carlo simulation study, with the original Hill and moment estimators, a bias-corrected moment estimator and one of the minimum-variance reduced-bias (MVRB) extreme value index estimators recently introduced in the literature. An empirical example in the field of finance is also provided.

Mots clés: Physical Sciences

M. Ivette Gomes, M. Isabel Fraga Alves, Paulo Araújo Santos. PORT Hill and moment estimators for heavy-tailed models. Communications in Statistics - Simulation and Computation, 2008, 37 (07), pp.1281-1306. ⟨10.1080/03610910802050910⟩. ⟨hal-00514326⟩