Abstract
{ "background": "Transport maintenance depots are critical infrastructure for road network efficiency and safety in developing nations. However, rigorous, quantitative methodologies for evaluating the impact of systemic interventions on their operational efficiency are lacking in the engineering literature, particularly for sub-Saharan Africa.", "purpose and objectives": "This article presents a novel methodological framework to quantify causal efficiency gains from planned upgrades to transport depot systems. The objective is to provide engineers and planners with a robust analytical tool for ex-post evaluation of infrastructure investments.", "methodology": "We develop a quasi-experimental difference-in-differences (DiD) model. The core statistical specification is $Y{dt} = \\beta0 + \\beta1 \\text{Treat}d + \\beta2 \\text{Post}t + \\delta (\\text{Treat}d \\cdot \\text{Post}t) + \\epsilon{dt}$, where $Y{dt}$ is a composite efficiency score for depot $d$ at time $t$. The key parameter $\\delta$ captures the average treatment effect. Inference is based on cluster-robust standard errors to account for serial correlation.", "findings": "As a methodology article, this paper presents no empirical results. The framework's application is demonstrated through a simulated case study, illustrating that a failure to control for pre-existing trends can lead to a substantial overestimation of the treatment effect—by approximately 40% in the illustrative scenario.", "conclusion": "The proposed DiD framework provides a rigorous, transportable methodology for evaluating depot maintenance interventions. It directly addresses common confounding factors in observational engineering data, moving beyond simple before-after comparisons.", "recommendations": "We recommend that engineering authorities adopt this causal inference approach for post-implementation project audits. Future research should integrate this model with detailed engineering performance indicators, such as vehicle turnaround time and spare parts inventory turnover.", "key words": "Causal inference, infrastructure management, quasi-experimental design, transport engineering, maintenance systems", "contribution