The Integration of Multiple Data Sources for HIV/AIDS Incidence and Prevalence Estimation
Open Access
Author:
Sheng, Ben
Graduate Program:
Statistics
Degree:
Doctor of Philosophy
Document Type:
Dissertation
Date of Defense:
February 24, 2021
Committee Members:
Le Bao, Dissertation Advisor/Co-Advisor Le Bao, Committee Chair/Co-Chair Runze Li, Committee Member Aleksandra B Slavkovic, Committee Member Xun Cao, Outside Member Ephraim Mont Hanks, Program Head/Chair
Keywords:
antenatal clinic surveillance HIV prevalence statistical models antenatal clinic surveillance HIV prevalence statistical models routine HIV testing among pregnant women Antenatal clinic Unlinked anonymous HIV testing Routine HIV testing Calibration parameter Linear mixed-effects model weakly supervised learning semi-supervised learning logistic regression contingency table HIV recency HIV incidence
Abstract:
Since HIV was first identified in the early 1980s, its prevalence has increased dramatically, and the disease has become a global health crisis. While substantial progress has been made in recent years, much work is still needed in order to end the HIV/AIDS epidemic. As part of the solution, we need accurate HIV incidence and prevalence estimates by location and subpopulation; this would enable effective resource allocation in prevention and treatment. In this dissertation, we describe methods to improve estimation of HIV/AIDS incidence and prevalence by integrating multiple data sources.
