Accounting for Response Misclassification and Covariate Measurement Error Using a Random Effects Logit Model

• Published in: Communications in statistics. Simulation and computation Vol. 41; no. 9; pp. 1623 - 1636
• Main Author: Roy, Surupa
• Format: Journal Article
• Language: English
• Published: Colchester Taylor & Francis Group 01.10.2012; Taylor & Francis; Taylor & Francis Ltd
• Subjects: Economic models; Exact sciences and technology; Mathematics; MCMC; Measurement error; Metropolis-Hastings algorithm; Misclassification; Numerical analysis; Numerical analysis. Scientific computation; Numerical methods in probability and statistics; Primary 62; Random effects logit model; Sciences and techniques of general use; Secondary 62F15; Studies; MCMC; Misclassification error; Metropolis-Hastings algorithm; Covariate; Statistical simulation; Epidemiology; Markov chain; Binary response; Random effect; Logit model; Misclassification; Measurement error; Secondary 62F15; Bayes estimation; Monte Carlo method; Metropolis Hastings algorithm; Random error; Primary 62; Bad classification; Logistic model; Logistic distribution; Statistical method; Regression coefficient; Logistic regression; Regression model; Classification error; Numerical simulation; Random effects logit model
• ISSN: 0361-0918; 1532-4141
• DOI: 10.1080/03610918.2011.611312

Often in longitudinal data arising out of epidemiologic studies, measurement error in covariates and/or classification errors in binary responses may be present. The goal of the present work is to develop a random effects logistic regression model that corrects for the classification errors in binary responses and/or measurement error in covariates. The analysis is carried out under a Bayesian set up. Simulation study reveals the effect of ignoring measurement error and/or classification errors on the estimates of the regression coefficients.