Confidence Intervals for Prevalence Estimates from Complex Surveys with Imperfect Assays

TL;DR

This paper introduces new methods for constructing confidence intervals to accurately estimate disease prevalence from complex survey data, accounting for imperfect diagnostic tests and various sampling designs.

Contribution

It develops a unified approach for confidence intervals in surveys with imperfect tests and demonstrates improved coverage over existing methods.

Findings

Methods guarantee coverage in simulations

Applied to SARS-CoV-2 seroprevalence survey

Outperforms competing approaches in accuracy

Abstract

We present several related methods for creating confidence intervals to assess disease prevalence in variety of survey sampling settings. These include simple random samples with imperfect tests, weighted sampling with perfect tests, and weighted sampling with imperfect tests, with the first two settings considered special cases of the third. Our methods use survey results and measurements of test sensitivity and specificity to construct melded confidence intervals. We demonstrate that our methods appear to guarantee coverage in simulated settings, while competing methods are shown to achieve much lower than nominal coverage. We apply our method to a seroprevalence survey of SARS-CoV-2 in undiagnosed adults in the United States between May and July 2020.