A regression model for the copula graphic estimator

Simon M.S. LO, Ralf A. WILKE

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

Abstract

We suggest a pragmatic extension of the non-parametric copula-graphic estimator to a depending competing risks model with covariates. Our model is an attractive empirical approach for practitioners in many disciplines as it does not require knowledge of the marginal distributions. Although non-observable and only set-identifiable in most applications, classical duration models typically impose ad-hoc assumptions on their functional forms. Instead of directly estimating these distributions, we suggest a plug-in regression framework which utilises an estimator for the observable cumulative incidence curves which specification can be visually inspected. We perform simulations and estimate an unemployment duration model to demonstrate the advantages of our model compared to classical duration models such as the Cox proportional hazard model.
Original languageEnglish
Pages (from-to)21 - 46
Number of pages26
JournalJournal of Econometric Methods
Volume3
Issue number1
Early online date5 Sep 2013
DOIs
Publication statusPublished - Jan 2014

Fingerprint

Duration Models
Copula
Regression Model
Estimator
Competing Risks Model
Cox Proportional Hazards Model
Unemployment
Plug-in
Marginal Distribution
Covariates
Incidence
Regression
Specification
Curve
Model
Estimate
Demonstrate
Graphics
Simulation

Keywords

  • Archimedean copula
  • dependent censoring
  • partial identification

Cite this

LO, Simon M.S. ; WILKE, Ralf A. / A regression model for the copula graphic estimator. In: Journal of Econometric Methods. 2014 ; Vol. 3, No. 1. pp. 21 - 46.
@article{af1c72f63320486f90d393858ca9059f,
title = "A regression model for the copula graphic estimator",
abstract = "We suggest a pragmatic extension of the non-parametric copula-graphic estimator to a depending competing risks model with covariates. Our model is an attractive empirical approach for practitioners in many disciplines as it does not require knowledge of the marginal distributions. Although non-observable and only set-identifiable in most applications, classical duration models typically impose ad-hoc assumptions on their functional forms. Instead of directly estimating these distributions, we suggest a plug-in regression framework which utilises an estimator for the observable cumulative incidence curves which specification can be visually inspected. We perform simulations and estimate an unemployment duration model to demonstrate the advantages of our model compared to classical duration models such as the Cox proportional hazard model.",
keywords = "Archimedean copula, dependent censoring, partial identification",
author = "LO, {Simon M.S.} and WILKE, {Ralf A.}",
year = "2014",
month = "1",
doi = "10.1515/jem-2012-0016",
language = "English",
volume = "3",
pages = "21 -- 46",
journal = "Journal of Econometric Methods",
issn = "2156-6674",
number = "1",

}

A regression model for the copula graphic estimator. / LO, Simon M.S.; WILKE, Ralf A.

In: Journal of Econometric Methods, Vol. 3, No. 1, 01.2014, p. 21 - 46.

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

TY - JOUR

T1 - A regression model for the copula graphic estimator

AU - LO, Simon M.S.

AU - WILKE, Ralf A.

PY - 2014/1

Y1 - 2014/1

N2 - We suggest a pragmatic extension of the non-parametric copula-graphic estimator to a depending competing risks model with covariates. Our model is an attractive empirical approach for practitioners in many disciplines as it does not require knowledge of the marginal distributions. Although non-observable and only set-identifiable in most applications, classical duration models typically impose ad-hoc assumptions on their functional forms. Instead of directly estimating these distributions, we suggest a plug-in regression framework which utilises an estimator for the observable cumulative incidence curves which specification can be visually inspected. We perform simulations and estimate an unemployment duration model to demonstrate the advantages of our model compared to classical duration models such as the Cox proportional hazard model.

AB - We suggest a pragmatic extension of the non-parametric copula-graphic estimator to a depending competing risks model with covariates. Our model is an attractive empirical approach for practitioners in many disciplines as it does not require knowledge of the marginal distributions. Although non-observable and only set-identifiable in most applications, classical duration models typically impose ad-hoc assumptions on their functional forms. Instead of directly estimating these distributions, we suggest a plug-in regression framework which utilises an estimator for the observable cumulative incidence curves which specification can be visually inspected. We perform simulations and estimate an unemployment duration model to demonstrate the advantages of our model compared to classical duration models such as the Cox proportional hazard model.

KW - Archimedean copula

KW - dependent censoring

KW - partial identification

U2 - 10.1515/jem-2012-0016

DO - 10.1515/jem-2012-0016

M3 - Journal Article (refereed)

VL - 3

SP - 21

EP - 46

JO - Journal of Econometric Methods

JF - Journal of Econometric Methods

SN - 2156-6674

IS - 1

ER -