A Hierarchical Model for Estimating HIV Epidemics

As the global HIV pandemic enters its fourth decade, increasing numbers of surveillance sites have been established which allows countries to look into the epidemics at a finer scale, e.g. at sub-national level. However, the epidemic models have been applied independently to the sub-national areas within countries. An important technical barrier is that the availability and quality of the data vary widely from area to area, and many areas lack data for deriving stable and reliable results. To improve the accuracy of the results in areas with little data, we propose a hierarchical model that utilizes information efficiently by assuming similar characteristics of the epidemics across areas within one country. The joint distribution of the parameters in the hierarchical model can be approximated directly from the results of independent fits without needing to the refit the data. As a result, the hierarchical model has better predictive ability than the independent model as shown in examples of multiple countries in Sub-Saharan Africa.