Improving estimates of prevalence by repeated testing

Suppose a screening or diagnostic test with unknown properties is to be used, not primarily for classifying individuals, but for estimating the prevalence of disease. Its sensitivity and specificity may be enhanced by applying it repeatedly to the same individuals, thus bringing the proportion of individuals with overall positive results closer to the true prevalence. Repeated testing also makes it possible to estimate the prevalence by maximum likelihood. Some simple designs for estimation are evaluated in terms of their accuracy and cost.