Covariate-adjusted regression for longitudinal data incorporating correlation between repeated measurements

Danh V. Nguyen, Damla Şentürk

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Summary We propose an estimation method that incorporates the correlation/covariance structure between repeated measurements in covariate-adjusted regression models for distorted longitudinal data. In this distorted data setting, neither the longitudinal response nor (possibly time-varying) predictors are directly observable. The unobserved response and predictors are assumed to be distorted/contaminated by unknown functions of a common observable confounder. The proposed estimation methodology adjusts for the distortion effects both in estimation of the covariance structure and in the regression parameters using generalized least squares. The finite-sample performance of the proposed estimators is studied numerically by means of simulations. The consistency and convergence rates of the proposed estimators are also established. The proposed method is illustrated with an application to data from a longitudinal study of cognitive and social development in children.

Original languageEnglish (US)
Pages (from-to)319-333
Number of pages15
JournalAustralian and New Zealand Journal of Statistics
Volume51
Issue number3
DOIs
StatePublished - Sep 2009

Fingerprint

Repeated Measurements
Longitudinal Data
Covariates
Regression
Covariance Structure
Predictors
Estimator
Generalized Least Squares
Longitudinal Study
Correlation Structure
Regression Model
Time-varying
Rate of Convergence
Unknown
Methodology
Longitudinal data
Simulation

Keywords

  • Binning
  • Clustered data
  • Covariance structure
  • General linear model
  • Generalized least squares
  • Multiplicative effect
  • Varying-coefficient models

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Covariate-adjusted regression for longitudinal data incorporating correlation between repeated measurements. / Nguyen, Danh V.; Şentürk, Damla.

In: Australian and New Zealand Journal of Statistics, Vol. 51, No. 3, 09.2009, p. 319-333.

Research output: Contribution to journalArticle

@article{7d811ac0319e4d3781168a3313ce335a,
title = "Covariate-adjusted regression for longitudinal data incorporating correlation between repeated measurements",
abstract = "Summary We propose an estimation method that incorporates the correlation/covariance structure between repeated measurements in covariate-adjusted regression models for distorted longitudinal data. In this distorted data setting, neither the longitudinal response nor (possibly time-varying) predictors are directly observable. The unobserved response and predictors are assumed to be distorted/contaminated by unknown functions of a common observable confounder. The proposed estimation methodology adjusts for the distortion effects both in estimation of the covariance structure and in the regression parameters using generalized least squares. The finite-sample performance of the proposed estimators is studied numerically by means of simulations. The consistency and convergence rates of the proposed estimators are also established. The proposed method is illustrated with an application to data from a longitudinal study of cognitive and social development in children.",
keywords = "Binning, Clustered data, Covariance structure, General linear model, Generalized least squares, Multiplicative effect, Varying-coefficient models",
author = "Nguyen, {Danh V.} and Damla Şent{\"u}rk",
year = "2009",
month = "9",
doi = "10.1111/j.1467-842X.2009.00547.x",
language = "English (US)",
volume = "51",
pages = "319--333",
journal = "Australian and New Zealand Journal of Statistics",
issn = "1369-1473",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Covariate-adjusted regression for longitudinal data incorporating correlation between repeated measurements

AU - Nguyen, Danh V.

AU - Şentürk, Damla

PY - 2009/9

Y1 - 2009/9

N2 - Summary We propose an estimation method that incorporates the correlation/covariance structure between repeated measurements in covariate-adjusted regression models for distorted longitudinal data. In this distorted data setting, neither the longitudinal response nor (possibly time-varying) predictors are directly observable. The unobserved response and predictors are assumed to be distorted/contaminated by unknown functions of a common observable confounder. The proposed estimation methodology adjusts for the distortion effects both in estimation of the covariance structure and in the regression parameters using generalized least squares. The finite-sample performance of the proposed estimators is studied numerically by means of simulations. The consistency and convergence rates of the proposed estimators are also established. The proposed method is illustrated with an application to data from a longitudinal study of cognitive and social development in children.

AB - Summary We propose an estimation method that incorporates the correlation/covariance structure between repeated measurements in covariate-adjusted regression models for distorted longitudinal data. In this distorted data setting, neither the longitudinal response nor (possibly time-varying) predictors are directly observable. The unobserved response and predictors are assumed to be distorted/contaminated by unknown functions of a common observable confounder. The proposed estimation methodology adjusts for the distortion effects both in estimation of the covariance structure and in the regression parameters using generalized least squares. The finite-sample performance of the proposed estimators is studied numerically by means of simulations. The consistency and convergence rates of the proposed estimators are also established. The proposed method is illustrated with an application to data from a longitudinal study of cognitive and social development in children.

KW - Binning

KW - Clustered data

KW - Covariance structure

KW - General linear model

KW - Generalized least squares

KW - Multiplicative effect

KW - Varying-coefficient models

UR - http://www.scopus.com/inward/record.url?scp=63549129382&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63549129382&partnerID=8YFLogxK

U2 - 10.1111/j.1467-842X.2009.00547.x

DO - 10.1111/j.1467-842X.2009.00547.x

M3 - Article

AN - SCOPUS:63549129382

VL - 51

SP - 319

EP - 333

JO - Australian and New Zealand Journal of Statistics

JF - Australian and New Zealand Journal of Statistics

SN - 1369-1473

IS - 3

ER -