A semiparametric regression cure model for interval-censored data

Hao Liu, Yu Shen

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Motivated by medical studies in which patients could be cured of disease but the disease event time may be subject to interval censoring, we present a semiparametric nonmixture cure model for the regression analysis of interval-censored time-to-event data. We develop semiparametric maximum likelihood estimation for the model using the expectation-maximization method for interval-censored data. The maximization step for the baseline function is nonparametric and numerically challenging. We develop an efficient and numerically stable algorithm via modern convex optimization techniques, yielding a self-consistency algorithm for the maximization step.We prove the strong consistency of the maximum likelihood estimators under the Hellinger distance, which is an appropriate metric for the asymptotic property of the estimators for interval-censored data. We assess the performance of the estimators in a simulation study with small to moderate sample sizes. To illustrate the method, we also analyze a real dataset from a medical study for the biochemical recurrence of prostate cancer among patients who have undergone radical prostatectomy. Supplemental materials for the computational algorithm are available online.

Original languageEnglish (US)
Pages (from-to)1168-1178
Number of pages11
JournalJournal of the American Statistical Association
Volume104
Issue number487
DOIs
StatePublished - Oct 14 2009
Externally publishedYes

Fingerprint

Cure Model
Semiparametric Regression
Interval-censored Data
Regression Model
Interval Censoring
Hellinger Distance
Estimator
Self-consistency
Semiparametric Estimation
Prostate Cancer
Expectation Maximization
Strong Consistency
Semiparametric Model
Computational Algorithm
Convex Optimization
Regression Analysis
Maximum Likelihood Estimation
Maximum Likelihood Estimator
Recurrence
Optimization Techniques

Keywords

  • Convex optimization
  • Hellinger consistency
  • Maximum likelihood estimation
  • Primal-dual interior-point method
  • Prostate cancer

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

A semiparametric regression cure model for interval-censored data. / Liu, Hao; Shen, Yu.

In: Journal of the American Statistical Association, Vol. 104, No. 487, 14.10.2009, p. 1168-1178.

Research output: Contribution to journalArticle

@article{a734fb9732d44bc5aa9222de11029c6c,
title = "A semiparametric regression cure model for interval-censored data",
abstract = "Motivated by medical studies in which patients could be cured of disease but the disease event time may be subject to interval censoring, we present a semiparametric nonmixture cure model for the regression analysis of interval-censored time-to-event data. We develop semiparametric maximum likelihood estimation for the model using the expectation-maximization method for interval-censored data. The maximization step for the baseline function is nonparametric and numerically challenging. We develop an efficient and numerically stable algorithm via modern convex optimization techniques, yielding a self-consistency algorithm for the maximization step.We prove the strong consistency of the maximum likelihood estimators under the Hellinger distance, which is an appropriate metric for the asymptotic property of the estimators for interval-censored data. We assess the performance of the estimators in a simulation study with small to moderate sample sizes. To illustrate the method, we also analyze a real dataset from a medical study for the biochemical recurrence of prostate cancer among patients who have undergone radical prostatectomy. Supplemental materials for the computational algorithm are available online.",
keywords = "Convex optimization, Hellinger consistency, Maximum likelihood estimation, Primal-dual interior-point method, Prostate cancer",
author = "Hao Liu and Yu Shen",
year = "2009",
month = "10",
day = "14",
doi = "10.1198/jasa.2009.tm07494",
language = "English (US)",
volume = "104",
pages = "1168--1178",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "487",

}

TY - JOUR

T1 - A semiparametric regression cure model for interval-censored data

AU - Liu, Hao

AU - Shen, Yu

PY - 2009/10/14

Y1 - 2009/10/14

N2 - Motivated by medical studies in which patients could be cured of disease but the disease event time may be subject to interval censoring, we present a semiparametric nonmixture cure model for the regression analysis of interval-censored time-to-event data. We develop semiparametric maximum likelihood estimation for the model using the expectation-maximization method for interval-censored data. The maximization step for the baseline function is nonparametric and numerically challenging. We develop an efficient and numerically stable algorithm via modern convex optimization techniques, yielding a self-consistency algorithm for the maximization step.We prove the strong consistency of the maximum likelihood estimators under the Hellinger distance, which is an appropriate metric for the asymptotic property of the estimators for interval-censored data. We assess the performance of the estimators in a simulation study with small to moderate sample sizes. To illustrate the method, we also analyze a real dataset from a medical study for the biochemical recurrence of prostate cancer among patients who have undergone radical prostatectomy. Supplemental materials for the computational algorithm are available online.

AB - Motivated by medical studies in which patients could be cured of disease but the disease event time may be subject to interval censoring, we present a semiparametric nonmixture cure model for the regression analysis of interval-censored time-to-event data. We develop semiparametric maximum likelihood estimation for the model using the expectation-maximization method for interval-censored data. The maximization step for the baseline function is nonparametric and numerically challenging. We develop an efficient and numerically stable algorithm via modern convex optimization techniques, yielding a self-consistency algorithm for the maximization step.We prove the strong consistency of the maximum likelihood estimators under the Hellinger distance, which is an appropriate metric for the asymptotic property of the estimators for interval-censored data. We assess the performance of the estimators in a simulation study with small to moderate sample sizes. To illustrate the method, we also analyze a real dataset from a medical study for the biochemical recurrence of prostate cancer among patients who have undergone radical prostatectomy. Supplemental materials for the computational algorithm are available online.

KW - Convex optimization

KW - Hellinger consistency

KW - Maximum likelihood estimation

KW - Primal-dual interior-point method

KW - Prostate cancer

UR - http://www.scopus.com/inward/record.url?scp=70349763102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349763102&partnerID=8YFLogxK

U2 - 10.1198/jasa.2009.tm07494

DO - 10.1198/jasa.2009.tm07494

M3 - Article

AN - SCOPUS:70349763102

VL - 104

SP - 1168

EP - 1178

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 487

ER -