Exponential tilt models for two-group comparison with censored data

Chi Wang, Zhiqiang Tan, Thomas Louis

Research output: Contribution to journalArticle

Abstract

We study application of the Exponential Tilt Model (ETM) to compare survival distributions in two groups. The ETM assumes a parametric form for the density ratio of the two distributions. It accommodates a broad array of parametric models such as the log-normal and gamma models and can be sufficiently flexible to allow for crossing hazard and crossing survival functions. We develop a nonparametric likelihood approach to estimate ETM parameters in the presence of censoring and establish related asymptotic results. We compare the ETM to the Proportional Hazards Model (PHM) in simulation studies. When the proportional hazards assumption is not satisfied but the ETM assumption is, the ETM has better power for testing the hypothesis of no difference between the two groups. And, importantly, when the ETM relation is not satisfied but the PHM assumption is, the ETM can still have power reasonably close to that of the PHM. Application of the ETM is illustrated by a gastrointestinal tumor study.

Original languageEnglish (US)
Pages (from-to)1102-1117
Number of pages16
JournalJournal of Statistical Planning and Inference
Volume141
Issue number3
DOIs
StatePublished - Mar 2011

Fingerprint

Censored Data
Tilt
Proportional Hazards Model
Hazards
Model
Nonparametric Likelihood
Censored data
Survival Distribution
Proportional Hazards
Survival Function
Censoring
Parametric Model
Hazard
Tumor
Simulation Study
Tumors
Testing

Keywords

  • Censored data
  • Exponential tilt model
  • Non-parametric likelihood
  • Proportional hazards model

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

Exponential tilt models for two-group comparison with censored data. / Wang, Chi; Tan, Zhiqiang; Louis, Thomas.

In: Journal of Statistical Planning and Inference, Vol. 141, No. 3, 03.2011, p. 1102-1117.

Research output: Contribution to journalArticle

@article{20f65738be4a4bf5ab33beed727c40b4,
title = "Exponential tilt models for two-group comparison with censored data",
abstract = "We study application of the Exponential Tilt Model (ETM) to compare survival distributions in two groups. The ETM assumes a parametric form for the density ratio of the two distributions. It accommodates a broad array of parametric models such as the log-normal and gamma models and can be sufficiently flexible to allow for crossing hazard and crossing survival functions. We develop a nonparametric likelihood approach to estimate ETM parameters in the presence of censoring and establish related asymptotic results. We compare the ETM to the Proportional Hazards Model (PHM) in simulation studies. When the proportional hazards assumption is not satisfied but the ETM assumption is, the ETM has better power for testing the hypothesis of no difference between the two groups. And, importantly, when the ETM relation is not satisfied but the PHM assumption is, the ETM can still have power reasonably close to that of the PHM. Application of the ETM is illustrated by a gastrointestinal tumor study.",
keywords = "Censored data, Exponential tilt model, Non-parametric likelihood, Proportional hazards model",
author = "Chi Wang and Zhiqiang Tan and Thomas Louis",
year = "2011",
month = "3",
doi = "10.1016/j.jspi.2010.09.009",
language = "English (US)",
volume = "141",
pages = "1102--1117",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Exponential tilt models for two-group comparison with censored data

AU - Wang, Chi

AU - Tan, Zhiqiang

AU - Louis, Thomas

PY - 2011/3

Y1 - 2011/3

N2 - We study application of the Exponential Tilt Model (ETM) to compare survival distributions in two groups. The ETM assumes a parametric form for the density ratio of the two distributions. It accommodates a broad array of parametric models such as the log-normal and gamma models and can be sufficiently flexible to allow for crossing hazard and crossing survival functions. We develop a nonparametric likelihood approach to estimate ETM parameters in the presence of censoring and establish related asymptotic results. We compare the ETM to the Proportional Hazards Model (PHM) in simulation studies. When the proportional hazards assumption is not satisfied but the ETM assumption is, the ETM has better power for testing the hypothesis of no difference between the two groups. And, importantly, when the ETM relation is not satisfied but the PHM assumption is, the ETM can still have power reasonably close to that of the PHM. Application of the ETM is illustrated by a gastrointestinal tumor study.

AB - We study application of the Exponential Tilt Model (ETM) to compare survival distributions in two groups. The ETM assumes a parametric form for the density ratio of the two distributions. It accommodates a broad array of parametric models such as the log-normal and gamma models and can be sufficiently flexible to allow for crossing hazard and crossing survival functions. We develop a nonparametric likelihood approach to estimate ETM parameters in the presence of censoring and establish related asymptotic results. We compare the ETM to the Proportional Hazards Model (PHM) in simulation studies. When the proportional hazards assumption is not satisfied but the ETM assumption is, the ETM has better power for testing the hypothesis of no difference between the two groups. And, importantly, when the ETM relation is not satisfied but the PHM assumption is, the ETM can still have power reasonably close to that of the PHM. Application of the ETM is illustrated by a gastrointestinal tumor study.

KW - Censored data

KW - Exponential tilt model

KW - Non-parametric likelihood

KW - Proportional hazards model

UR - http://www.scopus.com/inward/record.url?scp=78549294799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78549294799&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2010.09.009

DO - 10.1016/j.jspi.2010.09.009

M3 - Article

AN - SCOPUS:78549294799

VL - 141

SP - 1102

EP - 1117

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 3

ER -