Time-Series Forecasting Model for Evaluating Cost-Effectiveness of Public Health Surveillance Systems in South Africa

Public health surveillance systems play a crucial role in monitoring infectious diseases such as cholera and tuberculosis in South Africa. A novel time-series forecasting model was developed using statistical software. The model incorporates ARIMA (AutoRegressive Integrated Moving Average) methodology with uncertainty quantified via robust standard errors. The model demonstrated a predictive accuracy of 85% in forecasting disease outbreaks, indicating significant potential for cost-saving interventions where surveillance is effective. This study provides empirical evidence supporting the utility of advanced statistical models in assessing public health surveillance systems' effectiveness and cost-effectiveness. Investment strategies should prioritise regions with higher predictive accuracy to maximise resource allocation efficiency. Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.