An efficient confidence interval estimation for prevalence calculated from misclassified data

Abstract

The estimation of prevalence using a screening tool is done frequently in epidemiology research. The tools used for the estimation are usually associated with a certain level of misclassification. Additional adjustments are required to eliminate the bias in the prevalence and the confidence interval (CI) estimate. A frequently used method for this correction is by modifying the upper and lower limits, using sensitivity and specificity, increasing the width of the CI. The issue is exaggerated with a minimal sample size. Zhou and Li recently developed a method to estimate the CI using the Edgeworth expansion of the logit transformed binomial proportion. This article introduces a specialised tool by re-estimating the confidence limits adjusting for misclassified measurements, and assesses their characteristics through a simulation. The paper provides evidence that the re-estimated new interval performs better in the presence of misclassification.