Semiparametric density ratio modeling of survival data from a prevalent cohort

Hong Zhu, Jing Ning, Yu Shen, Jing Qin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this article, we consider methods for assessing covariate effects on survival outcome in the target population when data are collected under prevalent sampling. We investigate a flexible semiparametric density ratio model without the constraints of the constant disease incidence rate and discrete covariates as required in Shen and others 2012. For inference, we introduce two likelihood approaches with distinct computational algorithms. We first develop a full likelihood approach to obtain the most efficient estimators by an iterative algorithm. Under the density ratio model, we exploit the invariance property of uncensored failure times from the prevalent cohort and also propose a computationally convenient estimation procedure that uses a conditional pairwise likelihood. The empirical performance and efficiency of the two approaches are evaluated through simulation studies. The proposed methods are applied to the Surveillance, Epidemiology, and End Results Medicare linked data for women diagnosed with stage IV breast cancer.

Original languageEnglish (US)
Pages (from-to)62-75
Number of pages14
JournalBiostatistics
Volume18
Issue number1
DOIs
StatePublished - Jan 1 2017

Fingerprint

Survival Data
Covariates
Likelihood
Pairwise Likelihood
Conditional Likelihood
Efficient Estimator
Linked Data
Survival
Failure Time
Computational Algorithm
Epidemiology
Breast Cancer
Modeling
Surveillance
Iterative Algorithm
Invariance
Incidence
Health Services Needs and Demand
Simulation Study
Medicare

Keywords

  • Conditional pairwise likelihood
  • Density ratio model
  • Left-truncated right-censored data
  • Prevalent sampling
  • Profile likelihood

ASJC Scopus subject areas

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

Cite this

Semiparametric density ratio modeling of survival data from a prevalent cohort. / Zhu, Hong; Ning, Jing; Shen, Yu; Qin, Jing.

In: Biostatistics, Vol. 18, No. 1, 01.01.2017, p. 62-75.

Research output: Contribution to journalArticle

Zhu, Hong ; Ning, Jing ; Shen, Yu ; Qin, Jing. / Semiparametric density ratio modeling of survival data from a prevalent cohort. In: Biostatistics. 2017 ; Vol. 18, No. 1. pp. 62-75.
@article{26c6932a82014da9b2e09ad77e448ee7,
title = "Semiparametric density ratio modeling of survival data from a prevalent cohort",
abstract = "In this article, we consider methods for assessing covariate effects on survival outcome in the target population when data are collected under prevalent sampling. We investigate a flexible semiparametric density ratio model without the constraints of the constant disease incidence rate and discrete covariates as required in Shen and others 2012. For inference, we introduce two likelihood approaches with distinct computational algorithms. We first develop a full likelihood approach to obtain the most efficient estimators by an iterative algorithm. Under the density ratio model, we exploit the invariance property of uncensored failure times from the prevalent cohort and also propose a computationally convenient estimation procedure that uses a conditional pairwise likelihood. The empirical performance and efficiency of the two approaches are evaluated through simulation studies. The proposed methods are applied to the Surveillance, Epidemiology, and End Results Medicare linked data for women diagnosed with stage IV breast cancer.",
keywords = "Conditional pairwise likelihood, Density ratio model, Left-truncated right-censored data, Prevalent sampling, Profile likelihood",
author = "Hong Zhu and Jing Ning and Yu Shen and Jing Qin",
year = "2017",
month = "1",
day = "1",
doi = "10.1093/biostatistics/kxw028",
language = "English (US)",
volume = "18",
pages = "62--75",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "1",

}

TY - JOUR

T1 - Semiparametric density ratio modeling of survival data from a prevalent cohort

AU - Zhu, Hong

AU - Ning, Jing

AU - Shen, Yu

AU - Qin, Jing

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this article, we consider methods for assessing covariate effects on survival outcome in the target population when data are collected under prevalent sampling. We investigate a flexible semiparametric density ratio model without the constraints of the constant disease incidence rate and discrete covariates as required in Shen and others 2012. For inference, we introduce two likelihood approaches with distinct computational algorithms. We first develop a full likelihood approach to obtain the most efficient estimators by an iterative algorithm. Under the density ratio model, we exploit the invariance property of uncensored failure times from the prevalent cohort and also propose a computationally convenient estimation procedure that uses a conditional pairwise likelihood. The empirical performance and efficiency of the two approaches are evaluated through simulation studies. The proposed methods are applied to the Surveillance, Epidemiology, and End Results Medicare linked data for women diagnosed with stage IV breast cancer.

AB - In this article, we consider methods for assessing covariate effects on survival outcome in the target population when data are collected under prevalent sampling. We investigate a flexible semiparametric density ratio model without the constraints of the constant disease incidence rate and discrete covariates as required in Shen and others 2012. For inference, we introduce two likelihood approaches with distinct computational algorithms. We first develop a full likelihood approach to obtain the most efficient estimators by an iterative algorithm. Under the density ratio model, we exploit the invariance property of uncensored failure times from the prevalent cohort and also propose a computationally convenient estimation procedure that uses a conditional pairwise likelihood. The empirical performance and efficiency of the two approaches are evaluated through simulation studies. The proposed methods are applied to the Surveillance, Epidemiology, and End Results Medicare linked data for women diagnosed with stage IV breast cancer.

KW - Conditional pairwise likelihood

KW - Density ratio model

KW - Left-truncated right-censored data

KW - Prevalent sampling

KW - Profile likelihood

UR - http://www.scopus.com/inward/record.url?scp=85021369405&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021369405&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxw028

DO - 10.1093/biostatistics/kxw028

M3 - Article

VL - 18

SP - 62

EP - 75

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 1

ER -