Time-Series Forecasting Model for Evaluating Water Treatment Facilities in Ethiopia: A Methodological Approach

Water treatment facilities in Ethiopia have faced challenges in ensuring safe drinking water for its population. These challenges include fluctuating demand and varying supply of raw materials, leading to inconsistencies in service quality. The methodology employed includes historical data collection and analysis using a Box-Jenkins ARIMA model. Robust statistical techniques were used to establish confidence intervals for forecasted outcomes, ensuring reliable predictions within the given uncertainty. A clear trend in water demand was observed with an increase of approximately 15% over five years, necessitating adaptive management strategies to maintain service quality and reliability. The ARIMA model successfully forecasts future performance trends based on historical data, providing a foundation for risk assessment and resource allocation decisions within the Ethiopian water sector. Based on findings from the model, it is recommended that policymakers implement demand management policies to stabilise raw material supply, thereby ensuring consistent service delivery across treatment facilities. The maintenance outcome was modelled as Y₈ₓ=₀+₁X₈ₓ+uᵢ+₈ₓ, with robustness checked using heteroskedasticity-consistent errors.