{ "background": "The reliability of transport depot maintenance systems is critical for infrastructure sustainability. Previous studies on this topic in the region have often relied on cross-sectional data, limiting the ability to control for unobserved heterogeneity and analyse temporal dynamics.", "purpose and objectives": "This study aims to replicate and extend prior analyses by implementing a panel-data framework to estimate the reliability of transport depot maintenance systems. The objective is to provide a robust methodological evaluation and generate more reliable longitudinal estimates of system performance.", "methodology": "A replication study employing panel-data econometrics. The core model is a two-way fixed effects regression: $Reliability{it} = \\alpha + \\beta1 X{it} + \\mui + \\lambdat + \\epsilon{it}$, where $\\mui$ and $\\lambdat$ represent depot and year fixed effects. Inference is based on cluster-robust standard errors to account for serial correlation.", "findings": "The panel-data approach yields significantly different estimates compared to prior cross-sectional models. A key finding is that a 10% increase in scheduled preventative maintenance is associated with a 4.2 percentage point increase in system reliability (95% CI: 2.1, 6.3), an effect approximately 40% larger than previously reported.", "conclusion": "The application of panel-data methods reveals that earlier cross-sectional studies likely underestimated the efficacy of preventative maintenance programmes due to an inability to control for time-invariant depot-specific factors.", "recommendations": "Future research and performance audits of transport maintenance systems should adopt panel-data methodologies. Infrastructure policy should prioritise funding for scheduled preventative maintenance, as its impact is more substantial than earlier analyses suggested.", "key words": "panel data, replication study, maintenance reliability, transport infrastructure, fixed effects model, Nigeria", "contribution statement": "This study provides a novel panel dataset and demonstrates the empirical superiority of a fixed-effects modelling approach for analysing depot reliability, directly challenging prior methodological conventions in the region's engineering