Rank-based estimation for semiparametric accelerated failure time model under length-biased sampling

Sy Han Chiou, Gongjun Xu

Research output: Contribution to journalArticle

Abstract

Length-biased sampling appears in many observational studies, including epidemiological studies, labor economics and cancer screening trials. To accommodate sampling bias, which can lead to substantial estimation bias if ignored, we propose a class of doubly-weighted rank-based estimating equations under the accelerated failure time model. The general weighting structures considered in our estimating equations allow great flexibility and include many existing methods as special cases. Different approaches for constructing estimating equations are investigated, and the estimators are shown to be consistent and asymptotically normal. Moreover, we propose efficient computational procedures to solve the estimating equations and to estimate the variances of the estimators. Simulation studies show that the proposed estimators outperform the existing estimators. Moreover, real data from a dementia study and a Spanish unemployment duration study are analyzed to illustrate the proposed method.

Original languageEnglish (US)
Pages (from-to)483-500
Number of pages18
JournalStatistics and Computing
Volume27
Issue number2
DOIs
StatePublished - Mar 1 2017

Fingerprint

Biased Sampling
Accelerated Failure Time Model
Estimating Equation
Semiparametric Model
Sampling
Estimator
Screening
Personnel
Dementia
Economics
Observational Study
Unemployment
Weighting
Cancer
Flexibility
Simulation Study
Estimate

Keywords

  • Doubly-weighted estimating equation
  • Induced smoothing
  • Length-biased sampling
  • Resampling

Cite this

Rank-based estimation for semiparametric accelerated failure time model under length-biased sampling. / Chiou, Sy Han; Xu, Gongjun.

In: Statistics and Computing, Vol. 27, No. 2, 01.03.2017, p. 483-500.

Research output: Contribution to journalArticle

@article{e01b57f0e5c540409e8f4f83a6e38c1a,
title = "Rank-based estimation for semiparametric accelerated failure time model under length-biased sampling",
abstract = "Length-biased sampling appears in many observational studies, including epidemiological studies, labor economics and cancer screening trials. To accommodate sampling bias, which can lead to substantial estimation bias if ignored, we propose a class of doubly-weighted rank-based estimating equations under the accelerated failure time model. The general weighting structures considered in our estimating equations allow great flexibility and include many existing methods as special cases. Different approaches for constructing estimating equations are investigated, and the estimators are shown to be consistent and asymptotically normal. Moreover, we propose efficient computational procedures to solve the estimating equations and to estimate the variances of the estimators. Simulation studies show that the proposed estimators outperform the existing estimators. Moreover, real data from a dementia study and a Spanish unemployment duration study are analyzed to illustrate the proposed method.",
keywords = "Doubly-weighted estimating equation, Induced smoothing, Length-biased sampling, Resampling",
author = "Chiou, {Sy Han} and Gongjun Xu",
year = "2017",
month = "3",
day = "1",
doi = "10.1007/s11222-016-9634-5",
language = "English (US)",
volume = "27",
pages = "483--500",
journal = "Statistics and Computing",
issn = "0960-3174",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Rank-based estimation for semiparametric accelerated failure time model under length-biased sampling

AU - Chiou, Sy Han

AU - Xu, Gongjun

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Length-biased sampling appears in many observational studies, including epidemiological studies, labor economics and cancer screening trials. To accommodate sampling bias, which can lead to substantial estimation bias if ignored, we propose a class of doubly-weighted rank-based estimating equations under the accelerated failure time model. The general weighting structures considered in our estimating equations allow great flexibility and include many existing methods as special cases. Different approaches for constructing estimating equations are investigated, and the estimators are shown to be consistent and asymptotically normal. Moreover, we propose efficient computational procedures to solve the estimating equations and to estimate the variances of the estimators. Simulation studies show that the proposed estimators outperform the existing estimators. Moreover, real data from a dementia study and a Spanish unemployment duration study are analyzed to illustrate the proposed method.

AB - Length-biased sampling appears in many observational studies, including epidemiological studies, labor economics and cancer screening trials. To accommodate sampling bias, which can lead to substantial estimation bias if ignored, we propose a class of doubly-weighted rank-based estimating equations under the accelerated failure time model. The general weighting structures considered in our estimating equations allow great flexibility and include many existing methods as special cases. Different approaches for constructing estimating equations are investigated, and the estimators are shown to be consistent and asymptotically normal. Moreover, we propose efficient computational procedures to solve the estimating equations and to estimate the variances of the estimators. Simulation studies show that the proposed estimators outperform the existing estimators. Moreover, real data from a dementia study and a Spanish unemployment duration study are analyzed to illustrate the proposed method.

KW - Doubly-weighted estimating equation

KW - Induced smoothing

KW - Length-biased sampling

KW - Resampling

UR - http://www.scopus.com/inward/record.url?scp=84957638804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957638804&partnerID=8YFLogxK

U2 - 10.1007/s11222-016-9634-5

DO - 10.1007/s11222-016-9634-5

M3 - Article

AN - SCOPUS:84957638804

VL - 27

SP - 483

EP - 500

JO - Statistics and Computing

JF - Statistics and Computing

SN - 0960-3174

IS - 2

ER -