On Bayesian Estimation in Group Screening Designs without Errors in Decisions

Abstract

Group screening or testing has long been recognized as a safe and sensible alternative to one-at-a-time testing in applications wherein the prevalence rate p is small. In this paper, we developed an Empirical Bayes (EB) procedure to estimate p using a beta-type prior distribution and a squared error loss function. We showed that the Empirical Bayes (EB) estimator is preferred over the usual Maximum Likelihood Estimator (MLE) for small group sizes and small p. The methods were illustrated using group testing data from a prospective hepatitis C virus study that was conducted in China.