Least squares type estimation for Cox regression model and specification error

PL Gradowska, RM Cooke

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

A new estimation procedure for the Cox proportional hazards model is introduced. The method proposed employs the sample covariance matrix of model covariates and alternates between estimating the baseline cumulative hazard function and estimating model coefficients. It is shown that the estimating equation for model parameters resembles the least squares estimate in a linear regression model, where the outcome variable is the transformed event time. As a result an explicit expression for the difference in the parameter estimates between nested models can be derived. Nesting occurs when the covariates of one model are a subset of the covariates of the other. The new method applies mainly to the uncensored data, but its extension to the right censored observations is also proposed.
LanguageEnglish
Pages2288-2302
Number of pages15
JournalComputational Statistics and Data Analysis
Volume56
Issue number7
DOIs
Publication statusPublished - Jul 2012

Fingerprint

Cox Regression Model
Least Squares
Specification
Specifications
Covariates
Cumulative Hazard Function
Censored Observations
Nested Models
Sample Covariance Matrix
Cox Proportional Hazards Model
Least Squares Estimate
Estimating Equation
Linear Regression Model
Model
Hazards
Alternate
Baseline
Subset
Covariance matrix
Regression model

Keywords

  • cox regression
  • estimation
  • model specification
  • simulation
  • specification error

Cite this

@article{39ad416bc673463bbdc61a97ea110403,
title = "Least squares type estimation for Cox regression model and specification error",
abstract = "A new estimation procedure for the Cox proportional hazards model is introduced. The method proposed employs the sample covariance matrix of model covariates and alternates between estimating the baseline cumulative hazard function and estimating model coefficients. It is shown that the estimating equation for model parameters resembles the least squares estimate in a linear regression model, where the outcome variable is the transformed event time. As a result an explicit expression for the difference in the parameter estimates between nested models can be derived. Nesting occurs when the covariates of one model are a subset of the covariates of the other. The new method applies mainly to the uncensored data, but its extension to the right censored observations is also proposed.",
keywords = "cox regression, estimation, model specification, simulation, specification error",
author = "PL Gradowska and RM Cooke",
year = "2012",
month = "7",
doi = "10.1016/j.csda.2012.01.006",
language = "English",
volume = "56",
pages = "2288--2302",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
number = "7",

}

Least squares type estimation for Cox regression model and specification error. / Gradowska, PL; Cooke, RM.

In: Computational Statistics and Data Analysis, Vol. 56, No. 7, 07.2012, p. 2288-2302.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Least squares type estimation for Cox regression model and specification error

AU - Gradowska, PL

AU - Cooke, RM

PY - 2012/7

Y1 - 2012/7

N2 - A new estimation procedure for the Cox proportional hazards model is introduced. The method proposed employs the sample covariance matrix of model covariates and alternates between estimating the baseline cumulative hazard function and estimating model coefficients. It is shown that the estimating equation for model parameters resembles the least squares estimate in a linear regression model, where the outcome variable is the transformed event time. As a result an explicit expression for the difference in the parameter estimates between nested models can be derived. Nesting occurs when the covariates of one model are a subset of the covariates of the other. The new method applies mainly to the uncensored data, but its extension to the right censored observations is also proposed.

AB - A new estimation procedure for the Cox proportional hazards model is introduced. The method proposed employs the sample covariance matrix of model covariates and alternates between estimating the baseline cumulative hazard function and estimating model coefficients. It is shown that the estimating equation for model parameters resembles the least squares estimate in a linear regression model, where the outcome variable is the transformed event time. As a result an explicit expression for the difference in the parameter estimates between nested models can be derived. Nesting occurs when the covariates of one model are a subset of the covariates of the other. The new method applies mainly to the uncensored data, but its extension to the right censored observations is also proposed.

KW - cox regression

KW - estimation

KW - model specification

KW - simulation

KW - specification error

U2 - 10.1016/j.csda.2012.01.006

DO - 10.1016/j.csda.2012.01.006

M3 - Article

VL - 56

SP - 2288

EP - 2302

JO - Computational Statistics and Data Analysis

T2 - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 7

ER -