A General Class of Semiparametric Transformation Frailty Models for Nonproportional Hazards Survival Data

Sangbum Choi, Xuelin Huang

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We propose a semiparametrically efficient estimation of a broad class of transformation regression models for nonproportional hazards data. Classical transformation models are to be viewed from a frailty model paradigm, and the proposed method provides a unified approach that is valid for both continuous and discrete frailty models. The proposed models are shown to be flexible enough to model long-term follow-up survival data when the treatment effect diminishes over time, a case for which the PH or proportional odds assumption is violated, or a situation in which a substantial proportion of patients remains cured after treatment. Estimation of the link parameter in frailty distribution, considered to be unknown and possibly dependent on a time-independent covariates, is automatically included in the proposed methods. The observed information matrix is computed to evaluate the variances of all the parameter estimates. Our likelihood-based approach provides a natural way to construct simple statistics for testing the PH and proportional odds assumptions for usual survival data or testing the short- and long-term effects for survival data with a cure fraction. Simulation studies demonstrate that the proposed inference procedures perform well in realistic settings. Applications to two medical studies are provided.

Original languageEnglish
Pages (from-to)1126-1135
Number of pages10
JournalBiometrics
Volume68
Issue number4
DOIs
Publication statusPublished - 2012 Dec 1
Externally publishedYes

Fingerprint

Non-proportional Hazards
Frailty Model
Transformation Model
Survival Data
Proportional Odds
Proportional Hazards Models
Hazards
Survival
Observed Information
Frailty
Testing
Information Matrix
Efficient Estimation
Treatment Effects
Discrete Model
Covariates
Likelihood
Regression Model
Proportion
Paradigm

Keywords

  • Compound Poisson frailty
  • Counting process
  • Cure fraction
  • Discrete frailty
  • Nonparametric likelihood
  • Survival analysis
  • Transformation models

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability
  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Medicine(all)

Cite this

A General Class of Semiparametric Transformation Frailty Models for Nonproportional Hazards Survival Data. / Choi, Sangbum; Huang, Xuelin.

In: Biometrics, Vol. 68, No. 4, 01.12.2012, p. 1126-1135.

Research output: Contribution to journalArticle

@article{72b79c93ab2c462397bbfc8156d311a9,
title = "A General Class of Semiparametric Transformation Frailty Models for Nonproportional Hazards Survival Data",
abstract = "We propose a semiparametrically efficient estimation of a broad class of transformation regression models for nonproportional hazards data. Classical transformation models are to be viewed from a frailty model paradigm, and the proposed method provides a unified approach that is valid for both continuous and discrete frailty models. The proposed models are shown to be flexible enough to model long-term follow-up survival data when the treatment effect diminishes over time, a case for which the PH or proportional odds assumption is violated, or a situation in which a substantial proportion of patients remains cured after treatment. Estimation of the link parameter in frailty distribution, considered to be unknown and possibly dependent on a time-independent covariates, is automatically included in the proposed methods. The observed information matrix is computed to evaluate the variances of all the parameter estimates. Our likelihood-based approach provides a natural way to construct simple statistics for testing the PH and proportional odds assumptions for usual survival data or testing the short- and long-term effects for survival data with a cure fraction. Simulation studies demonstrate that the proposed inference procedures perform well in realistic settings. Applications to two medical studies are provided.",
keywords = "Compound Poisson frailty, Counting process, Cure fraction, Discrete frailty, Nonparametric likelihood, Survival analysis, Transformation models",
author = "Sangbum Choi and Xuelin Huang",
year = "2012",
month = "12",
day = "1",
doi = "10.1111/j.1541-0420.2012.01784.x",
language = "English",
volume = "68",
pages = "1126--1135",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - A General Class of Semiparametric Transformation Frailty Models for Nonproportional Hazards Survival Data

AU - Choi, Sangbum

AU - Huang, Xuelin

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We propose a semiparametrically efficient estimation of a broad class of transformation regression models for nonproportional hazards data. Classical transformation models are to be viewed from a frailty model paradigm, and the proposed method provides a unified approach that is valid for both continuous and discrete frailty models. The proposed models are shown to be flexible enough to model long-term follow-up survival data when the treatment effect diminishes over time, a case for which the PH or proportional odds assumption is violated, or a situation in which a substantial proportion of patients remains cured after treatment. Estimation of the link parameter in frailty distribution, considered to be unknown and possibly dependent on a time-independent covariates, is automatically included in the proposed methods. The observed information matrix is computed to evaluate the variances of all the parameter estimates. Our likelihood-based approach provides a natural way to construct simple statistics for testing the PH and proportional odds assumptions for usual survival data or testing the short- and long-term effects for survival data with a cure fraction. Simulation studies demonstrate that the proposed inference procedures perform well in realistic settings. Applications to two medical studies are provided.

AB - We propose a semiparametrically efficient estimation of a broad class of transformation regression models for nonproportional hazards data. Classical transformation models are to be viewed from a frailty model paradigm, and the proposed method provides a unified approach that is valid for both continuous and discrete frailty models. The proposed models are shown to be flexible enough to model long-term follow-up survival data when the treatment effect diminishes over time, a case for which the PH or proportional odds assumption is violated, or a situation in which a substantial proportion of patients remains cured after treatment. Estimation of the link parameter in frailty distribution, considered to be unknown and possibly dependent on a time-independent covariates, is automatically included in the proposed methods. The observed information matrix is computed to evaluate the variances of all the parameter estimates. Our likelihood-based approach provides a natural way to construct simple statistics for testing the PH and proportional odds assumptions for usual survival data or testing the short- and long-term effects for survival data with a cure fraction. Simulation studies demonstrate that the proposed inference procedures perform well in realistic settings. Applications to two medical studies are provided.

KW - Compound Poisson frailty

KW - Counting process

KW - Cure fraction

KW - Discrete frailty

KW - Nonparametric likelihood

KW - Survival analysis

KW - Transformation models

UR - http://www.scopus.com/inward/record.url?scp=84871651830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871651830&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2012.01784.x

DO - 10.1111/j.1541-0420.2012.01784.x

M3 - Article

C2 - 23005582

AN - SCOPUS:84871651830

VL - 68

SP - 1126

EP - 1135

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 4

ER -