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

Abstract

Employing annual time series data on the number of children (ages 0 – 14) newly infected with HIV in Kenya from 1990 – 2018, the study predicts the annual number of children who will be newly infected with HIV over the period 2019 – 2030. This piece of work applies the Box-Jenkins ARIMA methodology. The diagnostic ADF tests show that, V, the series under consideration is an I (1) variable. Based on the AIC, the study presents the ARIMA (1, 1, 4) model as the optimal model. The residual correlogram further shows that the residuals are not serially correlated and thus indicating that our model is stable and suitable for forecasting new HIV infections in children in Kenya. The results of the study indicate that the number of new pediatric HIV infections will increase from the estimated 8958 in 2019 to approximately 13591 new infections by 2030. A lot needs to be done in Kenya in order to save the lives of children from the HIV/AIDS epidemic. The study basically encourages the government of Kenya to intensively expand PMTCT coverage throughout the country.