Nonparametric species richness estimation under convexity constrain - Archive ouverte HAL Accéder directement au contenu
Rapport (Rapport Technique) Année : 2014

Nonparametric species richness estimation under convexity constrain

Résumé

We consider the estimation of the total number N of species based on the abundances of species that have been observed. We adopt a nonparametric approach where the true abundance distribution p is only supposed to be convex. From this assumption, we propose a de finition for convex abundance distributions. We use a least-squares estimate of the truncated version of p under the convexity constraint. We deduce two estimators of the total number of species, the asymptotic distribution of which are derived. We propose three di erent procedures, including a bootstrap one, to obtain a con dence interval for N. The performances of the estimators are assessed in a simulation study and compared with competitor. The proposed method is illustrated on several examples.

Dates et versions

hal-01197616 , version 1 (11-09-2015)

Identifiants

Citer

Cécile Durot, Sylvie Huet, François Koladjo, Stephane Robin. Nonparametric species richness estimation under convexity constrain. [Technical Report] 2014-1, auto-saisine. 2014, 36 p. ⟨hal-01197616⟩
109 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More