A conditional likelihood approach for regression analysis using biomarkers measured with batch-specific error

• Type of Material: Article
• Authors: Ming Wang, Emory University; W Dana Flanders, Emory University; Roberd M Bostick, Emory University; Qi Long, Emory University
• Language: English
• Date: 2012-12-20
• Publisher: Wiley: 12 months
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2012 John Wiley & Sons, Ltd.
• Final Published Version (URL): http://dx.doi.org/10.1002/sim.5473
• Title of Journal or Parent Work: Statistics in Medicine
• ISSN: 0277-6715
• Volume: 31
• Issue: 29
• Start Page: 3896
• End Page: 3906
• Grant/Funding Information: This work was partly supported by NIH/NCI grant CA114456 and NIH PHS Grant UL1 RR025008 from the Clinical and Translational Science Award program.
• Keywords: MUCOSA; Statistics & Probability; biomarker; exponential family; Physical Sciences; robust method; Mathematics; Life Sciences & Biomedicine; conditional likelihood; Research & Experimental Medicine; Science & Technology; Medicine, Research & Experimental; batch-specific error; Public, Environmental & Occupational Health; generalized linear models; MODELS; Mathematical & Computational Biology; Medical Informatics
• Research Categories: Biology, Biostatistics; Health Sciences, Oncology; Biology, Bioinformatics

Abstract

Measurement error is common in epidemiological and biomedical studies. When biomarkers are measured in batches or groups, measurement error is potentially correlated within each batch or group. In regression analysis, most existing methods are not applicable in the presence of batch-specific measurement error in predictors. We propose a robust conditional likelihood approach to account for batch-specific error in predictors when batch effect is additive and the predominant source of error, which requires no assumptions on the distribution of measurement error. Although a regression model with batch as a categorical covariable yields the same parameter estimates as the proposed conditional likelihood approach for linear regression, this result does not hold in general for all generalized linear models, in particular, logistic regression. Our simulation studies show that the conditional likelihood approach achieves better finite sample performance than the regression calibration approach or a naive approach without adjustment for measurement error. In the case of logistic regression, our proposed approach is shown to also outperform the regression approach with batch as a categorical covariate. In addition, we also examine a 'hybrid' approach combining the conditional likelihood method and the regression calibration method, which is shown in simulations to achieve good performance in the presence of both batch-specific and measurement-specific errors. We illustrate our method by using data from a colorectal adenoma study.