Assessing the Credibility of South Africa's Anti-Retroviral Treatment (ART) Eligibility Guidelines using Regression Discontinuity Designs

Abstract

HIV/AIDS is one of the deadliest diseases. In Southern Africa, it has caused millions of deaths and more infections. Regression discontinuity design can be used to evaluate the causal effect of treatment, and the distribution of this treatment depends on the running values on both sides of a fixed threshold (cutoff point). These designs can be used to analyse a case of HIV/AIDS and give causal estimates of the changing of the position of the threshold. Since its introduction by Thistlewaite and Campbell (1960) in 1960 it has been used by so many other scientists such as Black (1999), Ludwig and Miller (2005), Lee and Card (2007), Malaza et al. (2013), and many others. Most of the work done with the designs have been in the field of economics and education. However, in this paper, we will be using it in epidemiology as we deal with a case of HIV/AIDS in South Africa.