Efficient semiparametric mixture inferences on cure rate models for competing risks

Sangbum Choi, Xuelin Huang, Janice N. Cormier

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Cancer patients may die from causes other than the diagnosed cancer. In a study of patients treated for soft tissue sarcoma, the patients may die from the disease or die without experiencing disease recurrence. In addition, a substantial proportion of the patients will remain cancer-free after surgical resection of the tumour, and therefore will not be at increased risk of any type of failure. Our goal is to describe the effect of adjuvant chemotherapy simultaneously on the probabilities of long-term survival, death from cancer, or death from other causes. To this end, we propose a semiparametric mixture model to determine the effects of factors on the probability of occurrence, allowing the surviving fraction, and the hazard rate conditional on each of the failure types. These quantities are combined in the mixture approach using a multinomial logistic model and a class of semiparametric transformation models. Estimation of the regression and nonparametric parameters is achieved with a novel nonparametric maximum likelihood approach. Statistical inferences can be conveniently made from the inverse of the observed information matrix. Simulation studies show that the procedures work well in practical settings. The methodology is illustrated with data from the soft tissue sarcoma study.

Original languageEnglish
Pages (from-to)420-435
Number of pages16
JournalCanadian Journal of Statistics
Volume43
Issue number3
DOIs
Publication statusPublished - 2015 Sep 1
Externally publishedYes

Fingerprint

Cure Rate Model
Competing Risks
Cancer
Die
Soft Tissue
Semiparametric Model
Nonparametric Maximum Likelihood
Observed Information
Multinomial Model
Transformation Model
Information Matrix
Hazard Rate
Logistic Model
Chemotherapy
Statistical Inference
Mixture Model
Recurrence
Tumor
Proportion
Regression

Keywords

  • Cumulative incidence
  • Cure model
  • Martingale
  • Mixture
  • Nonparametric likelihood
  • Subgroup analysis
  • Transformation model

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Efficient semiparametric mixture inferences on cure rate models for competing risks. / Choi, Sangbum; Huang, Xuelin; Cormier, Janice N.

In: Canadian Journal of Statistics, Vol. 43, No. 3, 01.09.2015, p. 420-435.

Research output: Contribution to journalArticle

@article{e5a1bdd349cb403991d12b697a8ef30b,
title = "Efficient semiparametric mixture inferences on cure rate models for competing risks",
abstract = "Cancer patients may die from causes other than the diagnosed cancer. In a study of patients treated for soft tissue sarcoma, the patients may die from the disease or die without experiencing disease recurrence. In addition, a substantial proportion of the patients will remain cancer-free after surgical resection of the tumour, and therefore will not be at increased risk of any type of failure. Our goal is to describe the effect of adjuvant chemotherapy simultaneously on the probabilities of long-term survival, death from cancer, or death from other causes. To this end, we propose a semiparametric mixture model to determine the effects of factors on the probability of occurrence, allowing the surviving fraction, and the hazard rate conditional on each of the failure types. These quantities are combined in the mixture approach using a multinomial logistic model and a class of semiparametric transformation models. Estimation of the regression and nonparametric parameters is achieved with a novel nonparametric maximum likelihood approach. Statistical inferences can be conveniently made from the inverse of the observed information matrix. Simulation studies show that the procedures work well in practical settings. The methodology is illustrated with data from the soft tissue sarcoma study.",
keywords = "Cumulative incidence, Cure model, Martingale, Mixture, Nonparametric likelihood, Subgroup analysis, Transformation model",
author = "Sangbum Choi and Xuelin Huang and Cormier, {Janice N.}",
year = "2015",
month = "9",
day = "1",
doi = "10.1002/cjs.11256",
language = "English",
volume = "43",
pages = "420--435",
journal = "Canadian Journal of Statistics",
issn = "0319-5724",
publisher = "Statistical Society of Canada",
number = "3",

}

TY - JOUR

T1 - Efficient semiparametric mixture inferences on cure rate models for competing risks

AU - Choi, Sangbum

AU - Huang, Xuelin

AU - Cormier, Janice N.

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Cancer patients may die from causes other than the diagnosed cancer. In a study of patients treated for soft tissue sarcoma, the patients may die from the disease or die without experiencing disease recurrence. In addition, a substantial proportion of the patients will remain cancer-free after surgical resection of the tumour, and therefore will not be at increased risk of any type of failure. Our goal is to describe the effect of adjuvant chemotherapy simultaneously on the probabilities of long-term survival, death from cancer, or death from other causes. To this end, we propose a semiparametric mixture model to determine the effects of factors on the probability of occurrence, allowing the surviving fraction, and the hazard rate conditional on each of the failure types. These quantities are combined in the mixture approach using a multinomial logistic model and a class of semiparametric transformation models. Estimation of the regression and nonparametric parameters is achieved with a novel nonparametric maximum likelihood approach. Statistical inferences can be conveniently made from the inverse of the observed information matrix. Simulation studies show that the procedures work well in practical settings. The methodology is illustrated with data from the soft tissue sarcoma study.

AB - Cancer patients may die from causes other than the diagnosed cancer. In a study of patients treated for soft tissue sarcoma, the patients may die from the disease or die without experiencing disease recurrence. In addition, a substantial proportion of the patients will remain cancer-free after surgical resection of the tumour, and therefore will not be at increased risk of any type of failure. Our goal is to describe the effect of adjuvant chemotherapy simultaneously on the probabilities of long-term survival, death from cancer, or death from other causes. To this end, we propose a semiparametric mixture model to determine the effects of factors on the probability of occurrence, allowing the surviving fraction, and the hazard rate conditional on each of the failure types. These quantities are combined in the mixture approach using a multinomial logistic model and a class of semiparametric transformation models. Estimation of the regression and nonparametric parameters is achieved with a novel nonparametric maximum likelihood approach. Statistical inferences can be conveniently made from the inverse of the observed information matrix. Simulation studies show that the procedures work well in practical settings. The methodology is illustrated with data from the soft tissue sarcoma study.

KW - Cumulative incidence

KW - Cure model

KW - Martingale

KW - Mixture

KW - Nonparametric likelihood

KW - Subgroup analysis

KW - Transformation model

UR - http://www.scopus.com/inward/record.url?scp=84938983369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938983369&partnerID=8YFLogxK

U2 - 10.1002/cjs.11256

DO - 10.1002/cjs.11256

M3 - Article

AN - SCOPUS:84938983369

VL - 43

SP - 420

EP - 435

JO - Canadian Journal of Statistics

JF - Canadian Journal of Statistics

SN - 0319-5724

IS - 3

ER -