A Bayesian Hierarchical Model for Efficiency Diagnostics in Uganda's Transport Maintenance Depot Systems

Transport maintenance depot systems are critical infrastructure for economic development, yet their operational efficiency in many developing nations remains poorly quantified. Current diagnostic methods often lack the statistical rigour to handle heterogeneous depot data and inherent operational uncertainties. This study develops and applies a novel Bayesian hierarchical model to diagnose efficiency across a national network of transport maintenance depots. The objective is to provide a robust, probabilistic framework for identifying systemic inefficiencies and quantifying potential gains. A Bayesian hierarchical model was formulated, central to which is the efficiency parameter hetaⱼ Gamma (, ) for depot j, with hyperpriors on and to share information across the network. Operational data on resource inputs and work-order outputs from multiple depots were analysed using Hamiltonian Monte Carlo sampling to obtain posterior distributions for all parameters. The model identified substantial variation in technical efficiency, with posterior credible intervals for depot-level hetaⱼ revealing that nearly 40% of facilities operated below 65% of potential output. The hierarchical structure showed that inefficiencies were more strongly associated with logistical supply chains than with workforce size. The proposed model provides a statistically robust diagnostic tool that quantifies efficiency while formally accounting for uncertainty and shared operational characteristics across a depot network. Infrastructure policy should prioritise interventions targeting logistical bottlenecks. Depot managers should adopt probabilistic benchmarking, as provided by this model, for continuous performance monitoring and resource allocation. Bayesian inference, infrastructure management, technical efficiency, maintenance logistics, probabilistic modelling This paper presents a novel application of Bayesian hierarchical modelling to engineering systems management, delivering a new diagnostic framework that explicitly quantifies uncertainty in depot efficiency for informed decision-making.