Semiparametric regression with time-dependent coefficients for failure time data analysis

Zhangsheng Yu, Xihong Lin

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We propose a working independent profile likelihood method for the semiparametric time-varying coefficient model with correlation. Kernel likelihood is used to estimate time-varying coefficients. Profile likelihood for the parametric coefficients is formed by plugging in the nonparametric estimator. For independent data, the estimator is asymptotically normal and achieves the asymptotic semiparametric efficiency bound. We evaluate the performance of proposed nonparametric kernel estimator and the profile estimator, and apply the method to the western Kenya parasitemia data.

Original languageEnglish
Pages (from-to)853-869
Number of pages17
JournalStatistica Sinica
Volume20
Issue number2
StatePublished - Apr 2010

Fingerprint

Semiparametric Regression
Time-varying Coefficients
Failure Time Data
Profile Likelihood
Nonparametric Estimator
Data analysis
Semiparametric Efficiency
Estimator
Varying Coefficient Model
Asymptotic Efficiency
Kernel Estimator
Likelihood Methods
Coefficient
Likelihood
kernel
Evaluate
Estimate
Semiparametric regression
Coefficients
Profile

Keywords

  • Clustered survival data
  • Efficiency
  • Estimating equation
  • Kernel smoothing
  • Marginal model
  • Profile likelihood
  • Sandwich estimator

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Semiparametric regression with time-dependent coefficients for failure time data analysis. / Yu, Zhangsheng; Lin, Xihong.

In: Statistica Sinica, Vol. 20, No. 2, 04.2010, p. 853-869.

Research output: Contribution to journalArticle

@article{9efb74fc5273468cae97ca0611cc98da,
title = "Semiparametric regression with time-dependent coefficients for failure time data analysis",
abstract = "We propose a working independent profile likelihood method for the semiparametric time-varying coefficient model with correlation. Kernel likelihood is used to estimate time-varying coefficients. Profile likelihood for the parametric coefficients is formed by plugging in the nonparametric estimator. For independent data, the estimator is asymptotically normal and achieves the asymptotic semiparametric efficiency bound. We evaluate the performance of proposed nonparametric kernel estimator and the profile estimator, and apply the method to the western Kenya parasitemia data.",
keywords = "Clustered survival data, Efficiency, Estimating equation, Kernel smoothing, Marginal model, Profile likelihood, Sandwich estimator",
author = "Zhangsheng Yu and Xihong Lin",
year = "2010",
month = "4",
language = "English",
volume = "20",
pages = "853--869",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "2",

}

TY - JOUR

T1 - Semiparametric regression with time-dependent coefficients for failure time data analysis

AU - Yu, Zhangsheng

AU - Lin, Xihong

PY - 2010/4

Y1 - 2010/4

N2 - We propose a working independent profile likelihood method for the semiparametric time-varying coefficient model with correlation. Kernel likelihood is used to estimate time-varying coefficients. Profile likelihood for the parametric coefficients is formed by plugging in the nonparametric estimator. For independent data, the estimator is asymptotically normal and achieves the asymptotic semiparametric efficiency bound. We evaluate the performance of proposed nonparametric kernel estimator and the profile estimator, and apply the method to the western Kenya parasitemia data.

AB - We propose a working independent profile likelihood method for the semiparametric time-varying coefficient model with correlation. Kernel likelihood is used to estimate time-varying coefficients. Profile likelihood for the parametric coefficients is formed by plugging in the nonparametric estimator. For independent data, the estimator is asymptotically normal and achieves the asymptotic semiparametric efficiency bound. We evaluate the performance of proposed nonparametric kernel estimator and the profile estimator, and apply the method to the western Kenya parasitemia data.

KW - Clustered survival data

KW - Efficiency

KW - Estimating equation

KW - Kernel smoothing

KW - Marginal model

KW - Profile likelihood

KW - Sandwich estimator

UR - http://www.scopus.com/inward/record.url?scp=77953319587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953319587&partnerID=8YFLogxK

M3 - Article

VL - 20

SP - 853

EP - 869

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 2

ER -