Censored data and measurement error - Université Paris Cité Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2015

Censored data and measurement error

Résumé

We consider random variables which can be subject to both censoring and measurement errors. When considering different practical situations, two different models can be written to describe such situations in which the measurement errors affect only the variable of interest or also the censoring variable. Different estimation strategies can be proposed to estimate the density or hazard rate of the underlying variables of interest. We explain these models and strategies and provide L 2-risk bounds for the data driven resulting estimators. Simulations illustrate the performances of the estimators. Lastly, the method is applied to a real data set.
Fichier principal
Vignette du fichier
Censure_erreur_ComteSamsonStirnemann.pdf (378.01 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01150296 , version 1 (10-05-2015)
hal-01150296 , version 2 (04-12-2015)

Identifiants

  • HAL Id : hal-01150296 , version 1

Citer

Fabienne Comte, Adeline Samson, Julien J. Stirnemann. Censored data and measurement error. 2015. ⟨hal-01150296v1⟩
387 Consultations
512 Téléchargements

Partager

Gmail Facebook X LinkedIn More