Estimating with kernel smoothers the mean of functional data in a finite population setting. A note on variance estimation in presence of partially observed trajectories

Affiliation auteurs!!!! Error affiliation !!!!
TitreEstimating with kernel smoothers the mean of functional data in a finite population setting. A note on variance estimation in presence of partially observed trajectories
Type de publicationJournal Article
Year of Publication2015
AuteursCardot H, De Moliner A, Goga C
JournalSTATISTICS & PROBABILITY LETTERS
Volume99
Pagination156-166
Date PublishedAPR
Type of ArticleArticle
ISSN0167-7152
Mots-clésFunctional data, Hajek estimator, Horvitz-Thompson estimator, Missing values, Nonparametric estimation, Survey sampling
Résumé

This paper studies, in a survey sampling framework with unequal probability sampling designs, three nonparametric kernel estimators for the mean curve in presence of discretized trajectories with missing values. Their pointwise variances are approximated thanks to linearization techniques. (C) 2015 Elsevier B.V. All rights reserved.
DOI10.1016/j.spl.2015.01.025