Statistical Methods for Predicting Malaria Incidences Using Data from Sudan

Area of Science:

• Epidemiology
• Public Health
• Time Series Analysis

Background:

• Malaria poses a significant public health burden in Sudan, affecting the entire population and straining government resources.
• Accurate forecasting of malaria incidence is essential for effective public health interventions and resource allocation.

Purpose of the Study:

• To develop and evaluate time series models for predicting future malaria incidence in Sudan.
• To identify the most effective forecasting method for different regions with unstable malaria transmission.

Main Methods:

• Monthly malaria incidence data from five Sudanese states were analyzed.
• Four time series forecasting methods were tested: Autoregressive Integrated Moving Average (ARIMA), exponential smoothing, transformation model, and moving average.

Main Results:

• The transformation model demonstrated superior performance in predicting malaria incidence in Gadaref, Gazira, North Kordofan, and Northern states.
• The moving average model showed better predictive accuracy for Khartoum.

Conclusions:

• Different time series models exhibit varying performance across regions in Sudan for malaria forecasting.
• Future research should explore hybrid models to enhance forecast accuracy for malaria incidence in Sudan.