Predicting disease risk by transformation models in the presence of unspecified subgroup membership

Qianqian Wang, Yanyuan Ma, Yuanjia Wang

Research output: Contribution to journalArticle

Abstract

Some biomedical studies lead to mixture data. When a subgroup membership is missing for some of the subjects in a study, the distribution of the outcome is a mixture of the subgroup-specific distributions. Taking into account the uncertain distribution of the group membership and the covariates, we model the relation between the disease onset time and the covariates through transformation models in each sub-population, and develop a nonparametric maximum likelihood-based estimation implemented through the EM algorithm along with its inference procedure. We propose methods to identify the covariates that have different effects or common effects in distinct populations, which enables parsimonious modeling and better understanding of the differences across populations. The methods are illustrated through extensive simulation studies and a data example.

Original languageEnglish (US)
Pages (from-to)1857-1878
Number of pages22
JournalStatistica Sinica
Volume27
Issue number4
DOIs
StatePublished - Oct 2017

Fingerprint

Transformation Model
Covariates
Subgroup
Nonparametric Maximum Likelihood
EM Algorithm
Simulation Study
Distinct
Modeling
Transformation model
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{e12852ead99c4e8bace641128cfbe837,
title = "Predicting disease risk by transformation models in the presence of unspecified subgroup membership",
abstract = "Some biomedical studies lead to mixture data. When a subgroup membership is missing for some of the subjects in a study, the distribution of the outcome is a mixture of the subgroup-specific distributions. Taking into account the uncertain distribution of the group membership and the covariates, we model the relation between the disease onset time and the covariates through transformation models in each sub-population, and develop a nonparametric maximum likelihood-based estimation implemented through the EM algorithm along with its inference procedure. We propose methods to identify the covariates that have different effects or common effects in distinct populations, which enables parsimonious modeling and better understanding of the differences across populations. The methods are illustrated through extensive simulation studies and a data example.",
author = "Qianqian Wang and Yanyuan Ma and Yuanjia Wang",
year = "2017",
month = "10",
doi = "10.5705/ss.202016.0199",
language = "English (US)",
volume = "27",
pages = "1857--1878",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "4",

}

Predicting disease risk by transformation models in the presence of unspecified subgroup membership. / Wang, Qianqian; Ma, Yanyuan; Wang, Yuanjia.

In: Statistica Sinica, Vol. 27, No. 4, 10.2017, p. 1857-1878.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting disease risk by transformation models in the presence of unspecified subgroup membership

AU - Wang, Qianqian

AU - Ma, Yanyuan

AU - Wang, Yuanjia

PY - 2017/10

Y1 - 2017/10

N2 - Some biomedical studies lead to mixture data. When a subgroup membership is missing for some of the subjects in a study, the distribution of the outcome is a mixture of the subgroup-specific distributions. Taking into account the uncertain distribution of the group membership and the covariates, we model the relation between the disease onset time and the covariates through transformation models in each sub-population, and develop a nonparametric maximum likelihood-based estimation implemented through the EM algorithm along with its inference procedure. We propose methods to identify the covariates that have different effects or common effects in distinct populations, which enables parsimonious modeling and better understanding of the differences across populations. The methods are illustrated through extensive simulation studies and a data example.

AB - Some biomedical studies lead to mixture data. When a subgroup membership is missing for some of the subjects in a study, the distribution of the outcome is a mixture of the subgroup-specific distributions. Taking into account the uncertain distribution of the group membership and the covariates, we model the relation between the disease onset time and the covariates through transformation models in each sub-population, and develop a nonparametric maximum likelihood-based estimation implemented through the EM algorithm along with its inference procedure. We propose methods to identify the covariates that have different effects or common effects in distinct populations, which enables parsimonious modeling and better understanding of the differences across populations. The methods are illustrated through extensive simulation studies and a data example.

UR - http://www.scopus.com/inward/record.url?scp=85029186061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029186061&partnerID=8YFLogxK

U2 - 10.5705/ss.202016.0199

DO - 10.5705/ss.202016.0199

M3 - Article

C2 - 29097879

AN - SCOPUS:85029186061

VL - 27

SP - 1857

EP - 1878

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 4

ER -