JMIR Publications

ABSTRACT

Background:

Population size, prevalence, and incidence are essential metrics that influence public health policy. However, stakeholders are frequently tasked with designing policy based on multiple (often incongruous) estimates of these variables, and often do so in the absence of a formal, transparent framework for reaching a consensus estimate.

Objective:

This study aims to describe a model to synthesize multiple study estimates while incorporating stakeholder knowledge, introduce an R Shiny application to implement the model, and demonstrate the model and application using real data.

Methods:

This study develops a Bayesian hierarchical model to synthesize multiple study estimates that allows the user to incorporate the quality of each estimate as a ‘confidence’ score. The model is implemented as a user-friendly R Shiny app, aimed at practitioners of population size estimation. The underlying Bayesian model is programmed in STAN for efficient sampling and computation.

Results:

The application is demonstrated using population size estimates (and accompanying confidence scores) of female sex workers and men who have sex with men in a country in sub-Saharan Africa. The consensus results incorporating confidence scores are compared to the case where they are absent, and the results with confidence scores are shown to perform better according to an application-supplied metric for explained variance.

Conclusions:

The utility of the model, including the incorporation of confidence scores, is demonstrated by a use case example.