A joint model of recurrent events and a terminal event with a nonparametric covariate function

Zhangsheng Yu, Lei Liu

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

We extend the shared frailty model of recurrent events and a dependent terminal event to allow for a nonparametric covariate function. We include a Gaussian random effect (frailty) in the intensity functions of both the recurrent and terminal events to capture correlation between the two processes. We employ the penalized cubic spline method to describe the nonparametric covariate function in the recurrent events model. We use Laplace approximation to evaluate the marginal penalized partial likelihood without a closed form. We also propose the variance estimates for regression coefficients. Numerical analysis results show that the proposed estimates perform well for both the nonparametric and parametric components. We apply this method to analyze the hospitalization rate of patients with heart failure in the presence of death.

Original languageEnglish
Pages (from-to)2683-2695
Number of pages13
JournalStatistics in Medicine
Volume30
Issue number22
DOIs
StatePublished - Sep 30 2011

Fingerprint

Recurrent Events
Joint Model
Covariates
Joints
Laplace Approximation
Penalized Splines
Heart Failure
Partial Likelihood
Frailty Model
Frailty
Penalized Likelihood
Intensity Function
Hospitalization
Cubic Spline
Regression Coefficient
Random Effects
Estimate
Numerical Analysis
Closed-form
Dependent

Keywords

  • Counting process
  • Informative censoring
  • Proportional hazards model
  • Smoothing parameter
  • Survival analysis

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

A joint model of recurrent events and a terminal event with a nonparametric covariate function. / Yu, Zhangsheng; Liu, Lei.

In: Statistics in Medicine, Vol. 30, No. 22, 30.09.2011, p. 2683-2695.

Research output: Contribution to journalArticle

@article{c03e8f07c2eb4a2a9fd79e0d23d65b53,
title = "A joint model of recurrent events and a terminal event with a nonparametric covariate function",
abstract = "We extend the shared frailty model of recurrent events and a dependent terminal event to allow for a nonparametric covariate function. We include a Gaussian random effect (frailty) in the intensity functions of both the recurrent and terminal events to capture correlation between the two processes. We employ the penalized cubic spline method to describe the nonparametric covariate function in the recurrent events model. We use Laplace approximation to evaluate the marginal penalized partial likelihood without a closed form. We also propose the variance estimates for regression coefficients. Numerical analysis results show that the proposed estimates perform well for both the nonparametric and parametric components. We apply this method to analyze the hospitalization rate of patients with heart failure in the presence of death.",
keywords = "Counting process, Informative censoring, Proportional hazards model, Smoothing parameter, Survival analysis",
author = "Zhangsheng Yu and Lei Liu",
year = "2011",
month = "9",
day = "30",
doi = "10.1002/sim.4297",
language = "English",
volume = "30",
pages = "2683--2695",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "22",

}

TY - JOUR

T1 - A joint model of recurrent events and a terminal event with a nonparametric covariate function

AU - Yu, Zhangsheng

AU - Liu, Lei

PY - 2011/9/30

Y1 - 2011/9/30

N2 - We extend the shared frailty model of recurrent events and a dependent terminal event to allow for a nonparametric covariate function. We include a Gaussian random effect (frailty) in the intensity functions of both the recurrent and terminal events to capture correlation between the two processes. We employ the penalized cubic spline method to describe the nonparametric covariate function in the recurrent events model. We use Laplace approximation to evaluate the marginal penalized partial likelihood without a closed form. We also propose the variance estimates for regression coefficients. Numerical analysis results show that the proposed estimates perform well for both the nonparametric and parametric components. We apply this method to analyze the hospitalization rate of patients with heart failure in the presence of death.

AB - We extend the shared frailty model of recurrent events and a dependent terminal event to allow for a nonparametric covariate function. We include a Gaussian random effect (frailty) in the intensity functions of both the recurrent and terminal events to capture correlation between the two processes. We employ the penalized cubic spline method to describe the nonparametric covariate function in the recurrent events model. We use Laplace approximation to evaluate the marginal penalized partial likelihood without a closed form. We also propose the variance estimates for regression coefficients. Numerical analysis results show that the proposed estimates perform well for both the nonparametric and parametric components. We apply this method to analyze the hospitalization rate of patients with heart failure in the presence of death.

KW - Counting process

KW - Informative censoring

KW - Proportional hazards model

KW - Smoothing parameter

KW - Survival analysis

UR - http://www.scopus.com/inward/record.url?scp=80052842320&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052842320&partnerID=8YFLogxK

U2 - 10.1002/sim.4297

DO - 10.1002/sim.4297

M3 - Article

VL - 30

SP - 2683

EP - 2695

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 22

ER -