"background": "Industrial machinery fleets in developing economies often operate below optimal yield, but robust diagnostic frameworks for systematic improvement are lacking. Existing evaluations are frequently descriptive or rely on retrospective data, limiting causal inference on intervention efficacy. ", "purpose and objectives": "This article presents a novel quasi-experimental framework designed to diagnose and measure yield improvement in industrial machinery fleets. The objective is to provide a structured methodology for engineering practitioners to identify causal drivers of performance gains. ", "methodology": "The proposed framework employs a non-equivalent groups design with pre- and post-intervention measurement. Fleets are assigned to treatment and control conditions based on operational similarity. The core yield metric is analysed using a difference-in-differences model: Y{it = \0 + \1 + \2 + \ (\) + \₈ₓ, where inference relies on cluster-robust standard errors at the fleet level. ", "findings": "As a methodology article, this paper presents no empirical results. However, the framework's diagnostic power is demonstrated through a simulated case study, where it correctly identifies a 12-percentage-point yield gain attributable to a targeted maintenance intervention, distinguishing it from seasonal effects. ", "conclusion": "The framework provides a rigorous, practicable alternative to observational studies for evaluating engineering interventions in industrial settings. It formalises the process of attributing yield changes to specific actions. ", "recommendations": "Practitioners should adopt this structured quasi-experimental approach for fleet diagnostics to strengthen evidence-based decision-making. Further application should test its adaptability across different industrial sectors and machinery types. ", "key words": "quasi-experimental design, yield diagnostics, industrial machinery, maintenance engineering, causal inference, developing economies", "contribution statement": "This paper provides the first formalised quasi-experimental methodology tailored for yield diagnostics in industrial machinery fleets, enabling engineers
Mwajuma Mwinyimvua (Sat,) studied this question.