Spline-based semiparametric projected generalized estimating equation method for panel count data

Lei Hua, Ying Zhang

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

We propose to analyze panel count data using a spline-based semiparametric projected generalized estimating equation (GEE) method with the proportional mean model E((t)Z) = Λ0(t) eβ0TZ. The natural logarithm of the baseline mean function, logΛ0(t), is approximated by a monotone cubic B-spline function. The estimates of regression parameters and spline coefficients are obtained by projecting the GEE estimates into the feasible domain using a weighted isotonic regression (IR). The proposed method avoids assuming any parametric structure of the baseline mean function or any stochastic model for the underlying counting process. Selection of the working covariance matrix that accounts for overdispersion improves the estimation efficiency and leads to less biased variance estimations. Simulation studies are conducted using different working covariance matrices in the GEE to investigate finite sample performance of the proposed method, to compare the estimation efficiency, and to explore the performance of different variance estimates in presence of overdispersion. Finally, the proposed method is applied to a real data set from a bladder tumor clinical trial. The Author 2011. Published by Oxford University Press. All rights reserved.

Original languageEnglish (US)
Pages (from-to)440-454
Number of pages15
JournalBiostatistics
Volume13
Issue number3
DOIs
StatePublished - Jul 1 2012
Externally publishedYes

Fingerprint

Generalized Estimating Equations
Count Data
Panel Data
Spline
Overdispersion
Covariance matrix
Baseline
Biased Estimation
Natural logarithm
Estimate
Isotonic Regression
Cubic B-spline
B-spline Function
Counting Process
Variance Estimation
Clinical Trials
Stochastic Model
Tumor
Monotone
Regression

Keywords

  • Counting process
  • Generalized estimating equation
  • Monotone B-splines
  • Overdispersion
  • Semiparametric model

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Spline-based semiparametric projected generalized estimating equation method for panel count data. / Hua, Lei; Zhang, Ying.

In: Biostatistics, Vol. 13, No. 3, 01.07.2012, p. 440-454.

Research output: Contribution to journalArticle

@article{006285af42174ee68d87edb8ee07b399,
title = "Spline-based semiparametric projected generalized estimating equation method for panel count data",
abstract = "We propose to analyze panel count data using a spline-based semiparametric projected generalized estimating equation (GEE) method with the proportional mean model E((t)Z) = Λ0(t) eβ0TZ. The natural logarithm of the baseline mean function, logΛ0(t), is approximated by a monotone cubic B-spline function. The estimates of regression parameters and spline coefficients are obtained by projecting the GEE estimates into the feasible domain using a weighted isotonic regression (IR). The proposed method avoids assuming any parametric structure of the baseline mean function or any stochastic model for the underlying counting process. Selection of the working covariance matrix that accounts for overdispersion improves the estimation efficiency and leads to less biased variance estimations. Simulation studies are conducted using different working covariance matrices in the GEE to investigate finite sample performance of the proposed method, to compare the estimation efficiency, and to explore the performance of different variance estimates in presence of overdispersion. Finally, the proposed method is applied to a real data set from a bladder tumor clinical trial. The Author 2011. Published by Oxford University Press. All rights reserved.",
keywords = "Counting process, Generalized estimating equation, Monotone B-splines, Overdispersion, Semiparametric model",
author = "Lei Hua and Ying Zhang",
year = "2012",
month = "7",
day = "1",
doi = "10.1093/biostatistics/kxr028",
language = "English (US)",
volume = "13",
pages = "440--454",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Spline-based semiparametric projected generalized estimating equation method for panel count data

AU - Hua, Lei

AU - Zhang, Ying

PY - 2012/7/1

Y1 - 2012/7/1

N2 - We propose to analyze panel count data using a spline-based semiparametric projected generalized estimating equation (GEE) method with the proportional mean model E((t)Z) = Λ0(t) eβ0TZ. The natural logarithm of the baseline mean function, logΛ0(t), is approximated by a monotone cubic B-spline function. The estimates of regression parameters and spline coefficients are obtained by projecting the GEE estimates into the feasible domain using a weighted isotonic regression (IR). The proposed method avoids assuming any parametric structure of the baseline mean function or any stochastic model for the underlying counting process. Selection of the working covariance matrix that accounts for overdispersion improves the estimation efficiency and leads to less biased variance estimations. Simulation studies are conducted using different working covariance matrices in the GEE to investigate finite sample performance of the proposed method, to compare the estimation efficiency, and to explore the performance of different variance estimates in presence of overdispersion. Finally, the proposed method is applied to a real data set from a bladder tumor clinical trial. The Author 2011. Published by Oxford University Press. All rights reserved.

AB - We propose to analyze panel count data using a spline-based semiparametric projected generalized estimating equation (GEE) method with the proportional mean model E((t)Z) = Λ0(t) eβ0TZ. The natural logarithm of the baseline mean function, logΛ0(t), is approximated by a monotone cubic B-spline function. The estimates of regression parameters and spline coefficients are obtained by projecting the GEE estimates into the feasible domain using a weighted isotonic regression (IR). The proposed method avoids assuming any parametric structure of the baseline mean function or any stochastic model for the underlying counting process. Selection of the working covariance matrix that accounts for overdispersion improves the estimation efficiency and leads to less biased variance estimations. Simulation studies are conducted using different working covariance matrices in the GEE to investigate finite sample performance of the proposed method, to compare the estimation efficiency, and to explore the performance of different variance estimates in presence of overdispersion. Finally, the proposed method is applied to a real data set from a bladder tumor clinical trial. The Author 2011. Published by Oxford University Press. All rights reserved.

KW - Counting process

KW - Generalized estimating equation

KW - Monotone B-splines

KW - Overdispersion

KW - Semiparametric model

UR - http://www.scopus.com/inward/record.url?scp=84863599112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863599112&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxr028

DO - 10.1093/biostatistics/kxr028

M3 - Article

C2 - 21926062

AN - SCOPUS:84863599112

VL - 13

SP - 440

EP - 454

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 3

ER -