Asymptotic behaviour of regular estimators

Authors

  • Jean Diebolt Université de Marne-la-Vallée
  • Armelle Guillou Université Paris VI

DOI:

https://doi.org/10.57805/revstat.v3i1.16

Keywords:

extreme values, domain of attraction, excesses, generalized Pareto distribution, maximum likelihood estimators

Abstract

The P.O.T. (Peaks-Over-Threshold) approach consists of using the generalized Pareto distribution (GPD) to approximate the distribution of excesses over thresholds. We use the maximum likelihood estimators, or some other ones satisfying regularity conditions, to estimate the parameters of the approximating distribution. We study the asymptotic bias of these estimators and also the functional bias of the estimated GPD.

Published

2005-06-30

How to Cite

Diebolt , J., & Guillou, A. (2005). Asymptotic behaviour of regular estimators. REVSTAT-Statistical Journal, 3(1), 18–44. https://doi.org/10.57805/revstat.v3i1.16