Competing risk regression models for epidemiologic data

Bryan M Lau, Stephen R. Cole, Stephen J Gange

Research output: Contribution to journalArticle

Abstract

Competing events can preclude the event of interest from occurring in epidemiologic data and can be analyzed by using extensions of survival analysis methods. In this paper, the authors outline 3 regression approaches for estimating 2 key quantities in competing risks analysis: the cause-specific relative hazard (csRH) and the subdistribution relative hazard (sdRH). They compare and contrast the structure of the risk sets and the interpretation of parameters obtained with these methods. They also demonstrate the use of these methods with data from the Women's Interagency HIV Study established in 1993, treating time to initiation of highly active antiretroviral therapy or to clinical disease progression as competing events. In our example, women with an injection drug use history were less likely than those without a history of injection drug use to initiate therapy prior to progression to acquired immunodeficiency syndrome or death by both measures of association (csRH=0.67, 95% confidence interval: 0.57, 0.80 and sdRH=0.60, 95% confidence interval: 0.50, 0.71). Moreover, the relative hazards for disease progression prior to treatment were elevated (csRH=1.71, 95% confidence interval: 1.37, 2.13 and sdRH=2.01, 95% confidence interval: 1.62, 2.51). Methods for competing risks should be used by epidemiologists, with the choice of method guided by the scientific question.

Original languageEnglish (US)
Pages (from-to)244-256
Number of pages13
JournalAmerican Journal of Epidemiology
Volume170
Issue number2
DOIs
StatePublished - Jul 2009

Fingerprint

Confidence Intervals
Disease Progression
Injections
Highly Active Antiretroviral Therapy
Survival Analysis
Pharmaceutical Preparations
Acquired Immunodeficiency Syndrome
HIV
Therapeutics
Epidemiologists

Keywords

  • Competing risks
  • Epidemiologic methods
  • Mixture model
  • Proportional hazards
  • Regression
  • Survival analysis

ASJC Scopus subject areas

  • Epidemiology

Cite this

Competing risk regression models for epidemiologic data. / Lau, Bryan M; Cole, Stephen R.; Gange, Stephen J.

In: American Journal of Epidemiology, Vol. 170, No. 2, 07.2009, p. 244-256.

Research output: Contribution to journalArticle

@article{a9ad3ce19c5b4305a7c4743f6019ef51,
title = "Competing risk regression models for epidemiologic data",
abstract = "Competing events can preclude the event of interest from occurring in epidemiologic data and can be analyzed by using extensions of survival analysis methods. In this paper, the authors outline 3 regression approaches for estimating 2 key quantities in competing risks analysis: the cause-specific relative hazard (csRH) and the subdistribution relative hazard (sdRH). They compare and contrast the structure of the risk sets and the interpretation of parameters obtained with these methods. They also demonstrate the use of these methods with data from the Women's Interagency HIV Study established in 1993, treating time to initiation of highly active antiretroviral therapy or to clinical disease progression as competing events. In our example, women with an injection drug use history were less likely than those without a history of injection drug use to initiate therapy prior to progression to acquired immunodeficiency syndrome or death by both measures of association (csRH=0.67, 95{\%} confidence interval: 0.57, 0.80 and sdRH=0.60, 95{\%} confidence interval: 0.50, 0.71). Moreover, the relative hazards for disease progression prior to treatment were elevated (csRH=1.71, 95{\%} confidence interval: 1.37, 2.13 and sdRH=2.01, 95{\%} confidence interval: 1.62, 2.51). Methods for competing risks should be used by epidemiologists, with the choice of method guided by the scientific question.",
keywords = "Competing risks, Epidemiologic methods, Mixture model, Proportional hazards, Regression, Survival analysis",
author = "Lau, {Bryan M} and Cole, {Stephen R.} and Gange, {Stephen J}",
year = "2009",
month = "7",
doi = "10.1093/aje/kwp107",
language = "English (US)",
volume = "170",
pages = "244--256",
journal = "American Journal of Epidemiology",
issn = "0002-9262",
publisher = "Oxford University Press",
number = "2",

}

TY - JOUR

T1 - Competing risk regression models for epidemiologic data

AU - Lau, Bryan M

AU - Cole, Stephen R.

AU - Gange, Stephen J

PY - 2009/7

Y1 - 2009/7

N2 - Competing events can preclude the event of interest from occurring in epidemiologic data and can be analyzed by using extensions of survival analysis methods. In this paper, the authors outline 3 regression approaches for estimating 2 key quantities in competing risks analysis: the cause-specific relative hazard (csRH) and the subdistribution relative hazard (sdRH). They compare and contrast the structure of the risk sets and the interpretation of parameters obtained with these methods. They also demonstrate the use of these methods with data from the Women's Interagency HIV Study established in 1993, treating time to initiation of highly active antiretroviral therapy or to clinical disease progression as competing events. In our example, women with an injection drug use history were less likely than those without a history of injection drug use to initiate therapy prior to progression to acquired immunodeficiency syndrome or death by both measures of association (csRH=0.67, 95% confidence interval: 0.57, 0.80 and sdRH=0.60, 95% confidence interval: 0.50, 0.71). Moreover, the relative hazards for disease progression prior to treatment were elevated (csRH=1.71, 95% confidence interval: 1.37, 2.13 and sdRH=2.01, 95% confidence interval: 1.62, 2.51). Methods for competing risks should be used by epidemiologists, with the choice of method guided by the scientific question.

AB - Competing events can preclude the event of interest from occurring in epidemiologic data and can be analyzed by using extensions of survival analysis methods. In this paper, the authors outline 3 regression approaches for estimating 2 key quantities in competing risks analysis: the cause-specific relative hazard (csRH) and the subdistribution relative hazard (sdRH). They compare and contrast the structure of the risk sets and the interpretation of parameters obtained with these methods. They also demonstrate the use of these methods with data from the Women's Interagency HIV Study established in 1993, treating time to initiation of highly active antiretroviral therapy or to clinical disease progression as competing events. In our example, women with an injection drug use history were less likely than those without a history of injection drug use to initiate therapy prior to progression to acquired immunodeficiency syndrome or death by both measures of association (csRH=0.67, 95% confidence interval: 0.57, 0.80 and sdRH=0.60, 95% confidence interval: 0.50, 0.71). Moreover, the relative hazards for disease progression prior to treatment were elevated (csRH=1.71, 95% confidence interval: 1.37, 2.13 and sdRH=2.01, 95% confidence interval: 1.62, 2.51). Methods for competing risks should be used by epidemiologists, with the choice of method guided by the scientific question.

KW - Competing risks

KW - Epidemiologic methods

KW - Mixture model

KW - Proportional hazards

KW - Regression

KW - Survival analysis

UR - http://www.scopus.com/inward/record.url?scp=67651112075&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67651112075&partnerID=8YFLogxK

U2 - 10.1093/aje/kwp107

DO - 10.1093/aje/kwp107

M3 - Article

C2 - 19494242

AN - SCOPUS:67651112075

VL - 170

SP - 244

EP - 256

JO - American Journal of Epidemiology

JF - American Journal of Epidemiology

SN - 0002-9262

IS - 2

ER -