Abstract Say that interest focuses on the relationship between an exposure variable and an outcome variable; however, the exposure variable is subject to measurement error. While exceptions have been identified, in almost all circumstances nondifferential measurement error leads to attenuated...

Case-control data with imprecise exposure measurements can be analyzed via Bayesian fitting of a retrospective discriminant analysis model. The parameters of interest are the regression coefficients in the prospective log-odds ratio for disease. Under a standard noninformative prior, the...