Correcting for measurement error in individual-level covariates in nonlinear mixed effects models.

Published

Journal Article

The nonlinear mixed effects model is used to represent data in pharmacokinetics, viral dynamics, and other areas where an objective is to elucidate associations among individual-specific model parameters and covariates; however, covariates may be measured with error. For additive measurement error, we show substitution of mismeasured covariates for true covariates may lead to biased estimators for fixed effects and random effects covariance parameters, while regression calibration may eliminate bias in fixed effects but fail to correct that in covariance parameters. We develop methods to take account of measurement error that correct this bias and may be implemented with standard software, and we demonstrate their utility via simulation and application to data from a study of HIV dynamics.

Full Text

Duke Authors

Cited Authors

  • Ko, H; Davidian, M

Published Date

  • June 2000

Published In

Volume / Issue

  • 56 / 2

Start / End Page

  • 368 - 375

PubMed ID

  • 10877291

Pubmed Central ID

  • 10877291

International Standard Serial Number (ISSN)

  • 0006-341X

Language

  • eng

Conference Location

  • United States