"background": "Municipal infrastructure asset management systems (MIAMS) in Kenya have been implemented with significant investment, yet systematic, longitudinal analysis of their cost-effectiveness is lacking. This gap hinders evidence-based policy and optimal resource allocation for critical urban engineering assets. ", "purpose and objectives": "This working paper develops and validates a time-series forecasting model to quantitatively evaluate the historical and projected cost-effectiveness of MIAMS. The objective is to provide a replicable methodological framework for engineering asset managers to predict future performance and justify investments. ", "methodology": "A novel autoregressive integrated moving average with exogenous variables (ARIMAX) model is specified as Yt = \ + =1^{p\ Yt-i + \ + =1^q\ -i + =1^k\ Xj, t, where Yt is the cost-effectiveness ratio and X₉, ₓ are exogenous municipal finance and asset condition variables. Model parameters are estimated using maximum likelihood, with robust standard errors to account for heteroskedasticity. ", "findings": "The model forecasts a gradual improvement in aggregate cost-effectiveness, with a projected increase of approximately 15-20% over the medium term, contingent on sustained capital expenditure. Forecast uncertainty, represented by 95% prediction intervals, widens significantly beyond the short term, indicating sensitivity to fiscal policy shocks. ", "conclusion": "The proposed ARIMAX model provides a technically robust framework for forecasting MIAMS performance, demonstrating that cost-effectiveness trends are predictable but subject to considerable fiscal uncertainty. ", "recommendations": "Municipal engineers should adopt similar forecasting techniques for long-term asset management planning. Policymakers must prioritise stable funding mechanisms to reduce forecast variance and realise projected efficiency gains. ", "key words": "asset management, cost-effectiveness, time-series forecasting, municipal infrastructure, ARIMAX, engineering economics", "contribution statement":
Mwangi et al. (Fri,) studied this question.