Joint Scale-Change Models for Recurrent Events and Failure Time

Gongjun Xu, Sy Han Chiou, Chiung Yu Huang, Mei Cheng Wang, Jun Yan

Research output: Contribution to journalArticle

Abstract

Recurrent event data arise frequently in various fields such as biomedical sciences, public health, engineering, and social sciences. In many instances, the observation of the recurrent event process can be stopped by the occurrence of a correlated failure event, such as treatment failure and death. In this article, we propose a joint scale-change model for the recurrent event process and the failure time, where a shared frailty variable is used to model the association between the two types of outcomes. In contrast to the popular Cox-type joint modeling approaches, the regression parameters in the proposed joint scale-change model have marginal interpretations. The proposed approach is robust in the sense that no parametric assumption is imposed on the distribution of the unobserved frailty and that we do not need the strong Poisson-type assumption for the recurrent event process. We establish consistency and asymptotic normality of the proposed semiparametric estimators under suitable regularity conditions. To estimate the corresponding variances of the estimators, we develop a computationally efficient resampling-based procedure. Simulation studies and an analysis of hospitalization data from the Danish Psychiatric Central Register illustrate the performance of the proposed method. Supplementary materials for this article are available online.

Original languageEnglish (US)
Pages (from-to)1-12
Number of pages12
JournalJournal of the American Statistical Association
DOIs
StateAccepted/In press - Apr 4 2017

Fingerprint

Recurrent Events
Failure Time
Frailty
Estimator
Marginal Model
Joint Modeling
Public Health
Social Sciences
Resampling
Regularity Conditions
Asymptotic Normality
Model
Siméon Denis Poisson
Regression
Simulation Study
Engineering
Estimate

Keywords

  • Accelerated failure time model
  • Frailty
  • Informative censoring
  • Marginal models
  • Semiparametric methods

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Joint Scale-Change Models for Recurrent Events and Failure Time. / Xu, Gongjun; Chiou, Sy Han; Huang, Chiung Yu; Wang, Mei Cheng; Yan, Jun.

In: Journal of the American Statistical Association, 04.04.2017, p. 1-12.

Research output: Contribution to journalArticle

@article{94cec502dd30484e800ebc7570bed43b,
title = "Joint Scale-Change Models for Recurrent Events and Failure Time",
abstract = "Recurrent event data arise frequently in various fields such as biomedical sciences, public health, engineering, and social sciences. In many instances, the observation of the recurrent event process can be stopped by the occurrence of a correlated failure event, such as treatment failure and death. In this article, we propose a joint scale-change model for the recurrent event process and the failure time, where a shared frailty variable is used to model the association between the two types of outcomes. In contrast to the popular Cox-type joint modeling approaches, the regression parameters in the proposed joint scale-change model have marginal interpretations. The proposed approach is robust in the sense that no parametric assumption is imposed on the distribution of the unobserved frailty and that we do not need the strong Poisson-type assumption for the recurrent event process. We establish consistency and asymptotic normality of the proposed semiparametric estimators under suitable regularity conditions. To estimate the corresponding variances of the estimators, we develop a computationally efficient resampling-based procedure. Simulation studies and an analysis of hospitalization data from the Danish Psychiatric Central Register illustrate the performance of the proposed method. Supplementary materials for this article are available online.",
keywords = "Accelerated failure time model, Frailty, Informative censoring, Marginal models, Semiparametric methods",
author = "Gongjun Xu and Chiou, {Sy Han} and Huang, {Chiung Yu} and Wang, {Mei Cheng} and Jun Yan",
year = "2017",
month = "4",
day = "4",
doi = "10.1080/01621459.2016.1173557",
language = "English (US)",
pages = "1--12",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Joint Scale-Change Models for Recurrent Events and Failure Time

AU - Xu, Gongjun

AU - Chiou, Sy Han

AU - Huang, Chiung Yu

AU - Wang, Mei Cheng

AU - Yan, Jun

PY - 2017/4/4

Y1 - 2017/4/4

N2 - Recurrent event data arise frequently in various fields such as biomedical sciences, public health, engineering, and social sciences. In many instances, the observation of the recurrent event process can be stopped by the occurrence of a correlated failure event, such as treatment failure and death. In this article, we propose a joint scale-change model for the recurrent event process and the failure time, where a shared frailty variable is used to model the association between the two types of outcomes. In contrast to the popular Cox-type joint modeling approaches, the regression parameters in the proposed joint scale-change model have marginal interpretations. The proposed approach is robust in the sense that no parametric assumption is imposed on the distribution of the unobserved frailty and that we do not need the strong Poisson-type assumption for the recurrent event process. We establish consistency and asymptotic normality of the proposed semiparametric estimators under suitable regularity conditions. To estimate the corresponding variances of the estimators, we develop a computationally efficient resampling-based procedure. Simulation studies and an analysis of hospitalization data from the Danish Psychiatric Central Register illustrate the performance of the proposed method. Supplementary materials for this article are available online.

AB - Recurrent event data arise frequently in various fields such as biomedical sciences, public health, engineering, and social sciences. In many instances, the observation of the recurrent event process can be stopped by the occurrence of a correlated failure event, such as treatment failure and death. In this article, we propose a joint scale-change model for the recurrent event process and the failure time, where a shared frailty variable is used to model the association between the two types of outcomes. In contrast to the popular Cox-type joint modeling approaches, the regression parameters in the proposed joint scale-change model have marginal interpretations. The proposed approach is robust in the sense that no parametric assumption is imposed on the distribution of the unobserved frailty and that we do not need the strong Poisson-type assumption for the recurrent event process. We establish consistency and asymptotic normality of the proposed semiparametric estimators under suitable regularity conditions. To estimate the corresponding variances of the estimators, we develop a computationally efficient resampling-based procedure. Simulation studies and an analysis of hospitalization data from the Danish Psychiatric Central Register illustrate the performance of the proposed method. Supplementary materials for this article are available online.

KW - Accelerated failure time model

KW - Frailty

KW - Informative censoring

KW - Marginal models

KW - Semiparametric methods

UR - http://www.scopus.com/inward/record.url?scp=85017446109&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017446109&partnerID=8YFLogxK

U2 - 10.1080/01621459.2016.1173557

DO - 10.1080/01621459.2016.1173557

M3 - Article

C2 - 28943684

AN - SCOPUS:85017446109

SP - 1

EP - 12

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

ER -