Tree-based censored regression with applications in insurance

被引：18

作者：

Lopez, Olivier ^{[1
]}

Milhaud, Xavier ^{[2
,3
]}

Therond, Pierre-E. ^{[2
,4
]}

机构：

[1] UPMC Univ Paris VI, Sorbonne Univ, Lab Stat Theor & Appl, CNRS,FRE 3684, 4 Pl Jussieu, F-75005 Paris, France

[2] Univ Lyon, UCBL, LSAF EA2429, ISFA, F-69007 Lyon, France

[3] CREST LFA Lab, 15 Blvd Gabriel Peri, F-92245 Malakoff, France

[4] Galea & Associes, 12 Ave Maine, F-75015 Paris, France

来源：

ELECTRONIC JOURNAL OF STATISTICS | 2016年 / 10卷 / 02期

关键词：

Survival analysis; censoring; regression tree; model selection; insurance; NONPARAMETRIC-ESTIMATION; QUANTILE REGRESSION; UNIFORM CONSISTENCY; SURVIVAL-DATA; MODEL;

D O I：

10.1214/16-EJS1189

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

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 involving insurance datasets. The first concerns income protection insurance, while the second deals with reserving in third-party liability insurance.

引用

页码：2685 / 2716

页数：32

共 50 条

[1] Tree-based multivariate regression and density estimation with right-censored data
Molinaro, AM
Dudoit, S
van der Laan, MJ
[J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2004, 90 (01) : 154 - 177
[2] Tree-based classification and regression Part 3: Tree-based procedures
Gunter, B
[J]. QUALITY PROGRESS, 1998, 31 (02) : 121 - 123
[3] Comparison of Tree-Based Ensembles in Application to Censored Data
Kretowska, Malgorzata
[J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING ICAISC 2014, PT I, 2014, 8467 : 551 - 560
[4] Regression tree-based active learning
Ashna Jose
João Paulo Almeida de Mendonça
Emilie Devijver
Noël Jakse
Valérie Monbet
Roberta Poloni
[J]. Data Mining and Knowledge Discovery, 2024, 38 : 420 - 460
[5] Regression tree-based active learning
Jose, Ashna
de Mendonca, Joao Paulo Almeida
Devijver, Emilie
Jakse, Noel
Monbet, Valerie
Poloni, Roberta
[J]. DATA MINING AND KNOWLEDGE DISCOVERY, 2024, 38 (02) : 420 - 460
[6] Tree-based regression for a circular response
Lund, UJ
[J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2002, 31 (09) : 1549 - 1560
[7] Tree-based model checking for logistic regression
Su, Xiaogang
[J]. STATISTICS IN MEDICINE, 2007, 26 (10) : 2154 - 2169
[8] A Tree-Based Solution to Nonlinear Regression Problem
Demir, Oguzhan
Mohaghegh, Mohammadreza N.
Delibalta, Ibrahim
Kozat, Suleyman S.
[J]. 2016 24TH SIGNAL PROCESSING AND COMMUNICATION APPLICATION CONFERENCE (SIU), 2016, : 1233 - 1236
[9] A note on the interpretation of tree-based regression models
Gottard, Anna
Vannucci, Giulia
Marchetti, Giovanni Maria
[J]. BIOMETRICAL JOURNAL, 2020, 62 (06) : 1564 - 1573
[10] Inductive learning of tree-based regression models
Torgo, L
[J]. AI COMMUNICATIONS, 2000, 13 (02) : 137 - 138

← 1 2 3 4 5 →