Influence Measures for CART Classification Trees - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Classification Année : 2015

Influence Measures for CART Classification Trees

Avner Bar-Hen
Servane Gey
  • Fonction : Auteur
  • PersonId : 854165
Jean-Michel Poggi
  • Fonction : Auteur
  • PersonId : 890448

Résumé

This paper deals with measuring the influence of observations on the results obtained with CART classification trees. To define the influence of individuals on the analysis, we use influence functions to propose some general criterions to measure the sensitivity of the CART analysis and its robustness. The proposals, based on jakknife trees, are organized around two lines: influence on predictions and influence on partitions. In addition, the analysis is extended to the pruned sequences of CART trees to produce a CART specific notion of influence. A numerical example, the well known spam dataset, is presented to illustrate the notions developed throughout the paper. A real dataset relating the administrative classification of cities surrounding Paris, France, to the characteristics of their tax revenues distribution, is finally analyzed using the new influence-based tools.
Fichier principal
Vignette du fichier
cart.influence.pdf (308.63 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00562039 , version 1 (02-02-2011)

Licence

Paternité - Pas d'utilisation commerciale - Partage selon les Conditions Initiales

Identifiants

Citer

Avner Bar-Hen, Servane Gey, Jean-Michel Poggi. Influence Measures for CART Classification Trees. Journal of Classification, 2015, 32 (1), pp.21-45. ⟨10.1007/s00357-015-9172-4⟩. ⟨hal-00562039⟩
365 Consultations
528 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More