Bayesian hierarchical models are increasingly used in engineering applications to analyse complex data structures, such as those found in maintenance depots systems within transportation networks. A Bayesian hierarchical model was developed to analyse data from multiple maintenance depots, accounting for both within-depot variability and depot heterogeneity. Uncertainty quantification was achieved through posterior credible intervals. The analysis revealed a significant improvement in depot efficiency with an estimated yield increase of 15% across all depots, indicating higher resource utilization and reduced downtime. Bayesian hierarchical modelling provided a nuanced understanding of maintenance depot performance, enabling targeted interventions to further optimise system operations. Implementing the identified strategies in selected depots could lead to broader adoption, resulting in cost savings and improved service delivery across the network. maintenance depots, Bayesian hierarchical model, yield improvement, Nigerian transportation systems The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.