Small Area Estimation of HIV Measures in Sub-Saharan Africa

• Activity Number: 340 - SPEED: Applications of Advanced Statistical Techniques in Complex Survey Data Analysis: Small Area Estimation, Propensity Scores, Multilevel Models, and More
• Type: Contributed
• Date/Time: Tuesday, July 31, 2018 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Sahar Zangeneh* and Jon Wakefield and Ann Duerr and Deborah Donnell
• Companies: Fred Hutchinson Cancer Research Center and Univ of Washington and Fred Hutch and Fred Hutch
• Keywords: Small Area Estimation; Bayesian Hierarchical Model; Complex Surveys; Spatial Model

Abstract

Despite declining rates in recent years, the HIV epidemic continues to be a global challenge. Availability of highly effective treatments not only improves the quality of life for people living with the disease, but also prevents transmission to those at risk. Sub-national estimates of HIV prevalence are crucial in targeting interventions and allocating resources effectively. Cross-sectional surveys are administered to achieve nationally representative data in countries experiencing a generalized epidemic. Such surveys involve complex, multistage probability sampling and designed to achieve a certain level of precision at the national level. Small area estimation, which uses the entire national data, is needed to obtain reliable estimates. We propose a Bayesian hierarchical model that allows for individual-level covariate information and spatial dependencies, while accounting for complex sampling designs. This will result in robust statistical inferences with good repeated sampling properties and will aid policy makers in designing effective intervention strategies.