PAEDIATRIC NEW HIV INFECTIONS IN ZAMBIA A BOX-JENKINS ARIMA APPROACH

Abstract

Using annual time series data on the number of children (ages 0 – 14) newly infected with HIV in Zambia from 1990 – 2018, the study predicts the annual number of children who will be newly infected with HIV over the period 2019 – 2030. The paper applies the Box-Jenkins ARIMA approach to modeling and forecasting. The diagnostic ADF tests show that, T, the series under consideration is an I (2) variable. Based on the AIC, the study presents the ARIMA (2, 2, 0) model as the parsimonious model. The diagnostic tests further indicate that the presented model is indeed stable and its residuals are not serially correlated and are also normally distributed. The results of the research indicate that the number of new HIV infections in children in Zambia is expected to go down significantly from as high as 5096 in 2019 to as low as 2185 new infections by 2030. While zero new pediatric HIV infections may not be realized anytime soon, it is important to note that if the government continues to scale up the PMTCT programme throughout the country, the burden of HIV can be minimized.