<![CDATA[This study evaluates the forecasting accuracy of three univariate time series models, Decomposition, Holt-Winter’s, and Seasonal Autoregressive Integrated Moving Average (SARIMA) for predicting monthly malaria fever cases from January 2008 to December 2024. Data were obtained from the Federal Medical Centre, Jalingo, and analyzed using the three models. Forecasting performance was assessed using Root Mean Square Error (RMSE) as the primary evaluation metric. Among the models, the SARIMA (0, 0, 1) × (1, 1, 2) demonstrated the lowest RMSE, indicating superior forecasting accuracy over the Decomposition and Holt-Winter’s methods. Seasonal trend analysis revealed that malaria fever cases tend to be higher from April to August, with June showing the highest seasonal index representing a 92% increase over the annual average. These findings highlight the SARIMA model’s effectiveness in capturing the seasonal patterns of malaria incidence and its utility for public health planning and intervention.]]>
Copyrights © 2025
