Tree-based censored regression with applications to insurance

Abstract : In this paper, we propose a regression tree procedure to estimate the conditional distribution of a variable which is not directly observed due to censoring. The model that we consider is motivated by applications in insurance, including the analysis of guarantees that involve durations, and claim reserving. We derive consistency results for our procedure, and for the selection of an optimal subtree using a pruning strategy. These theoretical results are supported by a simulation study, and two applications to insurance datasets. The first one concerns income protection insurance, while the second deals with reserving in third-party liability insurance.
Type de document :
Pré-publication, Document de travail
2015
Liste complète des métadonnées

Littérature citée [39 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01141228
Contributeur : Xavier Milhaud <>
Soumis le : vendredi 10 avril 2015 - 19:09:18
Dernière modification le : jeudi 17 janvier 2019 - 17:21:56
Document(s) archivé(s) le : mardi 18 avril 2017 - 16:37:37

Fichier

TreeCensoredRegression-LopezMi...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01141228, version 1

Relations

Citation

Olivier Lopez, Xavier Milhaud, Pierre-Emmanuel Thérond. Tree-based censored regression with applications to insurance. 2015. 〈hal-01141228〉

Partager

Métriques

Consultations de la notice

443

Téléchargements de fichiers

2977