A copula model for dependent competing risks

Ming Sum, Simon LO, R. A. WILKE

Research output: Journal PublicationsJournal Article (refereed)

33 Citations (Scopus)

Abstract

Many popular estimators for duration models require independent competing risks or independent censoring. In contrast, copula-based estimators are also consistent in the presence of dependent competing risks. We suggest a computationally convenient extension of the copula graphic estimator to a model with more than two dependent competing risks. We analyse the applicability of this estimator by means of simulations and unemployment duration data from Germany. We obtain evidence that our estimator yields nice results if the dependence structure is known and that it is a powerful tool for the assessment of the relevance of (in-)dependence assumptions in applied duration research.
Original languageEnglish
Pages (from-to)359-376
Number of pages18
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume59
Issue number2
DOIs
Publication statusPublished - 1 Jan 2010

Fingerprint

Copula Models
Competing Risks
Estimator
Dependent
Copula
Duration Models
Unemployment
Dependence Structure
Censoring
Competing risks
Simulation

Keywords

  • Archimedean copula
  • Dependent censoring
  • Duration of unemployment

Cite this

LO, Ming Sum, Simon ; WILKE, R. A. / A copula model for dependent competing risks. In: Journal of the Royal Statistical Society. Series C: Applied Statistics. 2010 ; Vol. 59, No. 2. pp. 359-376.
@article{3c7ad6c260d649e891a60768826b0679,
title = "A copula model for dependent competing risks",
abstract = "Many popular estimators for duration models require independent competing risks or independent censoring. In contrast, copula-based estimators are also consistent in the presence of dependent competing risks. We suggest a computationally convenient extension of the copula graphic estimator to a model with more than two dependent competing risks. We analyse the applicability of this estimator by means of simulations and unemployment duration data from Germany. We obtain evidence that our estimator yields nice results if the dependence structure is known and that it is a powerful tool for the assessment of the relevance of (in-)dependence assumptions in applied duration research.",
keywords = "Archimedean copula, Dependent censoring, Duration of unemployment",
author = "LO, {Ming Sum, Simon} and WILKE, {R. A.}",
year = "2010",
month = "1",
day = "1",
doi = "10.1111/j.1467-9876.2009.00695.x",
language = "English",
volume = "59",
pages = "359--376",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell Publishing Ltd",
number = "2",

}

A copula model for dependent competing risks. / LO, Ming Sum, Simon; WILKE, R. A.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, Vol. 59, No. 2, 01.01.2010, p. 359-376.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - A copula model for dependent competing risks

AU - LO, Ming Sum, Simon

AU - WILKE, R. A.

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Many popular estimators for duration models require independent competing risks or independent censoring. In contrast, copula-based estimators are also consistent in the presence of dependent competing risks. We suggest a computationally convenient extension of the copula graphic estimator to a model with more than two dependent competing risks. We analyse the applicability of this estimator by means of simulations and unemployment duration data from Germany. We obtain evidence that our estimator yields nice results if the dependence structure is known and that it is a powerful tool for the assessment of the relevance of (in-)dependence assumptions in applied duration research.

AB - Many popular estimators for duration models require independent competing risks or independent censoring. In contrast, copula-based estimators are also consistent in the presence of dependent competing risks. We suggest a computationally convenient extension of the copula graphic estimator to a model with more than two dependent competing risks. We analyse the applicability of this estimator by means of simulations and unemployment duration data from Germany. We obtain evidence that our estimator yields nice results if the dependence structure is known and that it is a powerful tool for the assessment of the relevance of (in-)dependence assumptions in applied duration research.

KW - Archimedean copula

KW - Dependent censoring

KW - Duration of unemployment

UR - http://commons.ln.edu.hk/sw_master/6522

U2 - 10.1111/j.1467-9876.2009.00695.x

DO - 10.1111/j.1467-9876.2009.00695.x

M3 - Journal Article (refereed)

VL - 59

SP - 359

EP - 376

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

IS - 2

ER -