Cox regression analysis in presence of collinearity

An application to assessment of health risks associated with occupational radiation exposure

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

This paper considers the analysis of time to event data in the presence of collinearity between covariates. In linear and logistic regression models, the ridge regression estimator has been applied as an alternative to the maximum likelihood estimator in the presence of collinearity. The advantage of the ridge regression estimator over the usual maximum likelihood estimator is that the former often has a smaller total mean square error and is thus more precise. In this paper, we generalized this approach for addressing collinearity to the Cox proportional hazards model. Simulation studies were conducted to evaluate the performance of the ridge regression estimator. Our approach was motivated by an occupational radiation study conducted at Oak Ridge National Laboratory to evaluate health risks associated with occupational radiation exposure in which the exposure tends to be correlated with possible confounders such as years of exposure and attained age. We applied the proposed methods to this study to evaluate the association of radiation exposure with all-cause mortality.

Original languageEnglish (US)
Pages (from-to)333-350
Number of pages18
JournalLifetime Data Analysis
Volume13
Issue number3
DOIs
StatePublished - Sep 2007

Fingerprint

Cox Regression
Collinearity
Health risks
Occupational Exposure
Regression Analysis
Regression analysis
Ridge Regression
Regression Estimator
Health
Logistic Models
Radiation
Maximum likelihood
Proportional Hazards Models
Maximum Likelihood Estimator
Evaluate
Linear Models
Mean square error
Cox Proportional Hazards Model
Mortality
Logistics

Keywords

  • Collinearity
  • Cox proportional hazards model
  • Occupational exposure
  • Ridge regression

ASJC Scopus subject areas

  • Applied Mathematics
  • Medicine(all)

Cite this

@article{34fa61a8e9db42a888352b5251980857,
title = "Cox regression analysis in presence of collinearity: An application to assessment of health risks associated with occupational radiation exposure",
abstract = "This paper considers the analysis of time to event data in the presence of collinearity between covariates. In linear and logistic regression models, the ridge regression estimator has been applied as an alternative to the maximum likelihood estimator in the presence of collinearity. The advantage of the ridge regression estimator over the usual maximum likelihood estimator is that the former often has a smaller total mean square error and is thus more precise. In this paper, we generalized this approach for addressing collinearity to the Cox proportional hazards model. Simulation studies were conducted to evaluate the performance of the ridge regression estimator. Our approach was motivated by an occupational radiation study conducted at Oak Ridge National Laboratory to evaluate health risks associated with occupational radiation exposure in which the exposure tends to be correlated with possible confounders such as years of exposure and attained age. We applied the proposed methods to this study to evaluate the association of radiation exposure with all-cause mortality.",
keywords = "Collinearity, Cox proportional hazards model, Occupational exposure, Ridge regression",
author = "Xue, {Xiaonan (Nan)} and Mimi Kim and Shore, {Roy E.}",
year = "2007",
month = "9",
doi = "10.1007/s10985-007-9045-1",
language = "English (US)",
volume = "13",
pages = "333--350",
journal = "Lifetime Data Analysis",
issn = "1380-7870",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Cox regression analysis in presence of collinearity

T2 - An application to assessment of health risks associated with occupational radiation exposure

AU - Xue, Xiaonan (Nan)

AU - Kim, Mimi

AU - Shore, Roy E.

PY - 2007/9

Y1 - 2007/9

N2 - This paper considers the analysis of time to event data in the presence of collinearity between covariates. In linear and logistic regression models, the ridge regression estimator has been applied as an alternative to the maximum likelihood estimator in the presence of collinearity. The advantage of the ridge regression estimator over the usual maximum likelihood estimator is that the former often has a smaller total mean square error and is thus more precise. In this paper, we generalized this approach for addressing collinearity to the Cox proportional hazards model. Simulation studies were conducted to evaluate the performance of the ridge regression estimator. Our approach was motivated by an occupational radiation study conducted at Oak Ridge National Laboratory to evaluate health risks associated with occupational radiation exposure in which the exposure tends to be correlated with possible confounders such as years of exposure and attained age. We applied the proposed methods to this study to evaluate the association of radiation exposure with all-cause mortality.

AB - This paper considers the analysis of time to event data in the presence of collinearity between covariates. In linear and logistic regression models, the ridge regression estimator has been applied as an alternative to the maximum likelihood estimator in the presence of collinearity. The advantage of the ridge regression estimator over the usual maximum likelihood estimator is that the former often has a smaller total mean square error and is thus more precise. In this paper, we generalized this approach for addressing collinearity to the Cox proportional hazards model. Simulation studies were conducted to evaluate the performance of the ridge regression estimator. Our approach was motivated by an occupational radiation study conducted at Oak Ridge National Laboratory to evaluate health risks associated with occupational radiation exposure in which the exposure tends to be correlated with possible confounders such as years of exposure and attained age. We applied the proposed methods to this study to evaluate the association of radiation exposure with all-cause mortality.

KW - Collinearity

KW - Cox proportional hazards model

KW - Occupational exposure

KW - Ridge regression

UR - http://www.scopus.com/inward/record.url?scp=34548575438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548575438&partnerID=8YFLogxK

U2 - 10.1007/s10985-007-9045-1

DO - 10.1007/s10985-007-9045-1

M3 - Article

VL - 13

SP - 333

EP - 350

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

SN - 1380-7870

IS - 3

ER -