This study evaluates the time-series forecasting models for municipal infrastructure asset systems in Tanzania, focusing on methodological advancements and efficiency gains. A replication of the original study's methodology was conducted using historical data from municipal infrastructure in Tanzania. The study employed ARIMA (AutoRegressive Integrated Moving Average) models for forecasting and analysed their predictive accuracy through statistical tests. The findings indicate that ARIMA (1, 0, 1) model outperformed other models with a mean absolute error of 5. 2% during the forecast period. This study confirms the effectiveness of ARIMA in forecasting municipal infrastructure asset systems in Tanzania and highlights its potential for improving efficiency gains. The findings suggest that further research should explore more complex models to enhance predictive accuracy, particularly focusing on seasonal variations in data. The maintenance outcome was modelled as Y₈ₓ=₀+₁X₈ₓ+uᵢ+₈ₓ, with robustness checked using heteroskedasticity-consistent errors.
Kabaka Sittu (Mon,) studied this question.