Abstract:
|
Developing design strategies to reduce study expense is an important job for the practicing biostatistician. When the goal is screening for infections, one approach is group testing (GT) in which samples are initially tested in pools. For small prevalence, this could result in a large reduction of the total number of tests required. Despite this, the use of group testing in medical studies has been limited, largely due to skepticism about the impact of pooling on the test accuracy. In the theoretical GT literature, it is customary to assume that the misclassification parameters are known and/or do not change with the group size, both highly questionable assumptions to many applied researchers. In this work, we explore how the failure of these assumptions might impact the efficacy of a design and, as a result, whether GT is currently feasible in medical screening. Specifically, we look at how incorrect assumptions about the sensitivity function can lead to poor estimation of the overall sensitivity and expected number of tests. Furthermore, if a validation study is used to estimate the misclassification parameters, we show that the sample sizes required are prohibitive in most cases
|