Forecasting HIV Incidence in Somalia Using Single and Hybrid Time Series Models: A Comparative Analysis

This upload contains the manuscript and supporting materials for a time series forecasting study of HIV incidence in Somalia. The study used annual secondary data on HIV incidence, all ages (per 1,000 uninfected population), covering the period 1990–2022 from the World Bank World Development Indicators database. The study applied single and hybrid time series models, including ARIMA, ETS, TBATS, Theta, NNAR, ARFIMA, and selected hybrid approaches, to evaluate historical trends and forecast HIV incidence for 2023–2029. Model performance was assessed using MAPE, sMAPE, and Theil’s U statistic. The findings indicate that HIV incidence in Somalia is projected to remain stable at approximately 0.10 per 1,000 uninfected population, while continued prevention, surveillance, and public health planning remain essential.