Vignette d'image

A new resampling method for sampling designs without replacement: the doubled half bootstrap

Auteur(s)
Date de parution
2014-10
In
Computational Statistics
Vol.
5
No
29
De la page
1345
A la page
1363
Mots-clés
Résumé
A new and very fast method of bootstrap for sampling without replacement from a finite population is proposed. This method can be used to estimate the variance in sampling with unequal inclusion probabilities and does not require artificial populations or utilization of bootstrap weights. The bootstrap samples are directly selected from the original sample. The bootstrap procedure contains two steps: in the first step, units are selected once with Poisson sampling using the same inclusion probabilities as the original design. In the second step, amongst the non-selected units, half of the units are randomly selected twice. This procedure enables us to efficiently estimate the variance. A set of simulations show the advantages of this new resampling method.
Lié au projet
URI
DOI
Autre version
http://link.springer.com/article/10.1007/s00180-014-0495-0
Type de publication
Resource Types::text::journal::journal article
Dossier(s) à télécharger