Identifiability of the Sign of Covariate Effects in the Competing Risks Model

Simon M.S. Lo, Ralf Wilke

Research output: Contribution to journalJournal articleResearchpeer-review

94 Downloads (Pure)

Abstract

We present a new framework for the identification of competing risks models, which also include Roy models. We show that by establishing a Hicksian-type decomposition, the direction of covariate effects on the marginal distributions of the competing risks model can be identified under weak restrictions. Our approach leaves the marginal distributions and their joint distribution completely unspecified, except that the associated copula is invariant in the covariates. Results from simulations and two data examples suggest that our method often outperforms existing comparable approaches in terms of the range of durations for which the direction of the covariate effect is identified, particularly for long duration.
Original languageEnglish
JournalEconometric Theory
Volume33
Issue number5
Pages (from-to)1186-1217
Number of pages32
ISSN0266-4666
DOIs
Publication statusPublished - 2017

Bibliographical note

Published online: 3. October 2016

Cite this

@article{0940352d6bca49149acc8a120ff75f7c,
title = "Identifiability of the Sign of Covariate Effects in the Competing Risks Model",
abstract = "We present a new framework for the identification of competing risks models, which also include Roy models. We show that by establishing a Hicksian-type decomposition, the direction of covariate effects on the marginal distributions of the competing risks model can be identified under weak restrictions. Our approach leaves the marginal distributions and their joint distribution completely unspecified, except that the associated copula is invariant in the covariates. Results from simulations and two data examples suggest that our method often outperforms existing comparable approaches in terms of the range of durations for which the direction of the covariate effect is identified, particularly for long duration.",
author = "Lo, {Simon M.S.} and Ralf Wilke",
note = "Published online: 3. October 2016",
year = "2017",
doi = "10.1017/S0266466616000372",
language = "English",
volume = "33",
pages = "1186--1217",
journal = "Econometric Theory",
issn = "0266-4666",
publisher = "Cambridge University Press",
number = "5",

}

Identifiability of the Sign of Covariate Effects in the Competing Risks Model. / Lo, Simon M.S.; Wilke, Ralf.

In: Econometric Theory, Vol. 33, No. 5, 2017, p. 1186-1217.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Identifiability of the Sign of Covariate Effects in the Competing Risks Model

AU - Lo, Simon M.S.

AU - Wilke, Ralf

N1 - Published online: 3. October 2016

PY - 2017

Y1 - 2017

N2 - We present a new framework for the identification of competing risks models, which also include Roy models. We show that by establishing a Hicksian-type decomposition, the direction of covariate effects on the marginal distributions of the competing risks model can be identified under weak restrictions. Our approach leaves the marginal distributions and their joint distribution completely unspecified, except that the associated copula is invariant in the covariates. Results from simulations and two data examples suggest that our method often outperforms existing comparable approaches in terms of the range of durations for which the direction of the covariate effect is identified, particularly for long duration.

AB - We present a new framework for the identification of competing risks models, which also include Roy models. We show that by establishing a Hicksian-type decomposition, the direction of covariate effects on the marginal distributions of the competing risks model can be identified under weak restrictions. Our approach leaves the marginal distributions and their joint distribution completely unspecified, except that the associated copula is invariant in the covariates. Results from simulations and two data examples suggest that our method often outperforms existing comparable approaches in terms of the range of durations for which the direction of the covariate effect is identified, particularly for long duration.

UR - https://sfx-45cbs.hosted.exlibrisgroup.com/45cbs?url_ver=Z39.88-2004&url_ctx_fmt=info:ofi/fmt:kev:mtx:ctx&ctx_enc=info:ofi/enc:UTF-8&ctx_ver=Z39.88-2004&rfr_id=info:sid/sfxit.com:azlist&sfx.ignore_date_threshold=1&rft.object_id=954925341738&rft.object_portfolio_id=&svc.holdings=yes&svc.fulltext=yes

U2 - 10.1017/S0266466616000372

DO - 10.1017/S0266466616000372

M3 - Journal article

VL - 33

SP - 1186

EP - 1217

JO - Econometric Theory

JF - Econometric Theory

SN - 0266-4666

IS - 5

ER -