Volume 19, 2015
|Page(s)||28 - 59|
|Published online||01 May 2015|
Tail index estimation based on survey data
1 MODAL’X - Université Paris Ouest, 92001 Nanterre, France
2 Laboratoire de Statistique, CREST, France
3 Laboratoire AGM - Université de Cergy-Pontoise, 95000 Cergy-Pontoise, France
4 Institut Mines-Télécom - LTCI UMR Télécom ParisTech/CNRS No. 5141, 75634 Paris, France.
Received: 12 August 2013
Revised: 5 February 2014
This paper is devoted to tail index estimation in the context of survey data. Assuming that the population of interest is described by a heavy-tailed statistical model, we prove that the survey scheme plays a crucial role in the design of consistent inference methods for extremes. As can be revealed by simulation experiments, ignoring the sampling plan generally induces a significant bias, jeopardizing the accuracy of the extreme value statistics thus computed. Focus is here on the celebrated Hill method for tail index estimation, it is shown how to modify it in order to take into account the survey design. Precisely, under specific conditions on the inclusion probabilities of first and second orders, we establish the consistency of the variant of the Hill estimator we propose. Additionally, its asymptotic normality is proved in a specific situation. Application of this limit result for building Gaussian confidence intervals is thoroughly discussed and illustrated by numerical results.
Mathematics Subject Classification: 62D05 / 62F12 / 62G32
Key words: Survey sampling / tail index estimation / Hill estimator / Poisson survey scheme / rejective sampling
© EDP Sciences, SMAI, 2015
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.