Options
Qualité, Lionel
Nom
Qualité, Lionel
Affiliation principale
Fonction
maître assistant
Email
lionel.qualite@unine.ch
Identifiants
Résultat de la recherche
Voici les éléments 1 - 2 sur 2
- PublicationMétadonnées seulementA comparison of conditional Poisson sampling versus unequal probability sampling with replacement(2008-4-5)The variance of the Horvitz–Thompson estimator for a fixed size ConditionalPoissonsampling scheme without replacement and with unequal inclusion probabilities is compared to the variance of the Hansen–Hurwitz estimator for asampling scheme with replacement. We show, using a theorem by Gabler, that the sampling design without replacement is more efficient than the sampling design with replacement.
- PublicationMétadonnées seulementSystematic sampling is a minimal support design(2007-3-23)
; ; In order to select a sample in a finite population of N units with given inclusion probabilities, it is possible to define asamplingdesign on at most N samples that have a positive probability of being selected. Designs defined on minimal sets of samples are called minimum supportdesigns. It is shown that, for any vector of inclusion probabilities, systematicsampling always provides a minimum supportdesign. This property makes it possible to extensively compute the samplingdesign and the joint inclusion probabilities. Random systematicsampling can be viewed as the random choice of a minimum supportdesign. However, even if the population is randomly sorted, a simple example shows that some joint inclusion probabilities can be equal to zero. Another way of randomly selecting a minimum supportdesign is proposed, in such a way that all the samples have a positive probability of being selected, and all the joint inclusion probabilities are positive.