Assessing the fit of parametric cure models

E. Paul Wileyto, Yimei Li, Jinbo Chen, Daniel F. Heitjan

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Survival data can contain an unknown fraction of subjects who are "cured" in the sense of not being at risk of failure. We describe such data with cure-mixture models, which separately model cure status and the hazard of failure among non-cured subjects. No diagnostic currently exists for evaluating the fit of such models; the popular Schoenfeld residual (Schoenfeld, 1982. Partial residuals for the proportional hazards regression-model. Biometrika 69, 239-241) is not applicable to data with cures. In this article, we propose a pseudo-residual, modeled on Schoenfeld's, to assess the fit of the survival regression in the non-cured fraction. Unlike Schoenfeld's approach, which tests the validity of the proportional hazards (PH) assumption, our method uses the full hazard and is thus also applicable to non-PH models. We derive the asymptotic distribution of the residuals and evaluate their performance by simulation in a range of parametric models. We apply our approach to data from a smoking cessation drug trial.

Original languageEnglish (US)
Pages (from-to)340-350
Number of pages11
JournalBiostatistics
Volume14
Issue number2
DOIs
StatePublished - Apr 1 2013

Fingerprint

Cure Model
Parametric Model
Proportional Hazards Models
Hazard Models
Smoking Cessation
Hazard
Non-proportional Hazards
Proportional Hazards Regression
Proportional Hazards
Smoking
Survival Data
Mixture Model
Pharmaceutical Preparations
Asymptotic distribution
Regression Model
Diagnostics
Drugs
Regression
Partial
Unknown

Keywords

  • Accelerated failure time
  • Long-term survivors
  • Proportional hazards
  • Residual analysis

ASJC Scopus subject areas

  • Statistics and Probability
  • Medicine(all)
  • Statistics, Probability and Uncertainty

Cite this

Assessing the fit of parametric cure models. / Wileyto, E. Paul; Li, Yimei; Chen, Jinbo; Heitjan, Daniel F.

In: Biostatistics, Vol. 14, No. 2, 01.04.2013, p. 340-350.

Research output: Contribution to journalArticle

Wileyto, E. Paul ; Li, Yimei ; Chen, Jinbo ; Heitjan, Daniel F. / Assessing the fit of parametric cure models. In: Biostatistics. 2013 ; Vol. 14, No. 2. pp. 340-350.
@article{f8b158aa6a6c4946adf441d99fca7aa7,
title = "Assessing the fit of parametric cure models",
abstract = "Survival data can contain an unknown fraction of subjects who are {"}cured{"} in the sense of not being at risk of failure. We describe such data with cure-mixture models, which separately model cure status and the hazard of failure among non-cured subjects. No diagnostic currently exists for evaluating the fit of such models; the popular Schoenfeld residual (Schoenfeld, 1982. Partial residuals for the proportional hazards regression-model. Biometrika 69, 239-241) is not applicable to data with cures. In this article, we propose a pseudo-residual, modeled on Schoenfeld's, to assess the fit of the survival regression in the non-cured fraction. Unlike Schoenfeld's approach, which tests the validity of the proportional hazards (PH) assumption, our method uses the full hazard and is thus also applicable to non-PH models. We derive the asymptotic distribution of the residuals and evaluate their performance by simulation in a range of parametric models. We apply our approach to data from a smoking cessation drug trial.",
keywords = "Accelerated failure time, Long-term survivors, Proportional hazards, Residual analysis",
author = "Wileyto, {E. Paul} and Yimei Li and Jinbo Chen and Heitjan, {Daniel F.}",
year = "2013",
month = "4",
day = "1",
doi = "10.1093/biostatistics/kxs043",
language = "English (US)",
volume = "14",
pages = "340--350",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "2",

}

TY - JOUR

T1 - Assessing the fit of parametric cure models

AU - Wileyto, E. Paul

AU - Li, Yimei

AU - Chen, Jinbo

AU - Heitjan, Daniel F.

PY - 2013/4/1

Y1 - 2013/4/1

N2 - Survival data can contain an unknown fraction of subjects who are "cured" in the sense of not being at risk of failure. We describe such data with cure-mixture models, which separately model cure status and the hazard of failure among non-cured subjects. No diagnostic currently exists for evaluating the fit of such models; the popular Schoenfeld residual (Schoenfeld, 1982. Partial residuals for the proportional hazards regression-model. Biometrika 69, 239-241) is not applicable to data with cures. In this article, we propose a pseudo-residual, modeled on Schoenfeld's, to assess the fit of the survival regression in the non-cured fraction. Unlike Schoenfeld's approach, which tests the validity of the proportional hazards (PH) assumption, our method uses the full hazard and is thus also applicable to non-PH models. We derive the asymptotic distribution of the residuals and evaluate their performance by simulation in a range of parametric models. We apply our approach to data from a smoking cessation drug trial.

AB - Survival data can contain an unknown fraction of subjects who are "cured" in the sense of not being at risk of failure. We describe such data with cure-mixture models, which separately model cure status and the hazard of failure among non-cured subjects. No diagnostic currently exists for evaluating the fit of such models; the popular Schoenfeld residual (Schoenfeld, 1982. Partial residuals for the proportional hazards regression-model. Biometrika 69, 239-241) is not applicable to data with cures. In this article, we propose a pseudo-residual, modeled on Schoenfeld's, to assess the fit of the survival regression in the non-cured fraction. Unlike Schoenfeld's approach, which tests the validity of the proportional hazards (PH) assumption, our method uses the full hazard and is thus also applicable to non-PH models. We derive the asymptotic distribution of the residuals and evaluate their performance by simulation in a range of parametric models. We apply our approach to data from a smoking cessation drug trial.

KW - Accelerated failure time

KW - Long-term survivors

KW - Proportional hazards

KW - Residual analysis

UR - http://www.scopus.com/inward/record.url?scp=84874834133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874834133&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxs043

DO - 10.1093/biostatistics/kxs043

M3 - Article

VL - 14

SP - 340

EP - 350

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 2

ER -