{ "background": "Transport maintenance depots in Nigeria face systemic risks from operational, logistical, and environmental factors, which compromise infrastructure integrity and service reliability. Current risk assessment methods often lack the flexibility to incorporate site-specific variability and expert judgement, leading to suboptimal resource allocation for mitigation. ", "purpose and objectives": "This case study presents a methodological evaluation of a novel Bayesian hierarchical model designed to quantify risk reduction within these complex depot systems. The objective is to demonstrate a robust framework for integrating sparse observational data with engineering judgement to inform maintenance prioritisation. ", "methodology": "A three-level hierarchical model was developed and applied to a network of depots. The core model structure is \ (\, \), where represents the failure rate for component j in depot i, with hyperparameters pooling information across the network. Prior distributions were informed by expert elicitation, and posterior inferences were drawn using Markov chain Monte Carlo sampling. ", "findings": "The model successfully synthesised disparate data sources, yielding posterior distributions for key risk parameters. A principal finding was a quantified reduction in predictive uncertainty, with the 95% credible interval for mean time between failures narrowing by approximately 40% compared to classical estimates. This allowed for a more precise ranking of depots by systemic vulnerability. ", "conclusion": "The Bayesian hierarchical approach provides a statistically rigorous and operationally actionable methodology for risk assessment in transport maintenance systems characterised by data scarcity and heterogeneity. ", "recommendations": "Infrastructure managers should adopt probabilistic risk models that formally incorporate uncertainty. Future implementations should integrate real-time sensor data to dynamically update the model, transitioning from periodic to condition-based maintenance planning. ", "key words": "Bayesian inference, hierarchical modelling, infrastructure risk, maintenance management, probabilistic methods, transport engineering", "contribution statement": "This study provides a novel, transferable framework for probabilistic risk assessment in infrastructure systems, demonstrating through a concrete case how Bayesian hierarchical modelling reduces
Okonkwo et al. (Wed,) studied this question.