{ "background": "The adoption of advanced process-control systems in engineering sectors is a critical driver of industrial efficiency and productivity. However, rigorous quantitative evaluations of the causal impact of policies and interventions promoting such adoption in developing economies are scarce, limiting evidence-based decision-making.", "purpose and objectives": "This study conducts a methodological evaluation of the difference-in-differences (DiD) model for measuring adoption rates of process-control systems. It aims to assess the model's robustness and applicability within the Kenyan engineering context, identifying key methodological challenges and prerequisites for valid inference.", "methodology": "A comparative study design was employed, synthesising longitudinal data from engineering firms. The core DiD model is specified as $Y{it} = \\beta0 + \\beta1 \\text{Treat}i + \\beta2 \\text{Post}t + \\delta (\\text{Treat}i \\cdot \\text{Post}t) + \\epsilon_{it}$, where $\\delta$ is the average treatment effect. Estimation employed robust standard errors clustered at the firm level to account for serial correlation.", "findings": "The analysis reveals that the DiD estimator is highly sensitive to the parallel trends assumption, with a violation leading to a significant overestimation of the treatment effect by approximately 18 percentage points in simulated scenarios. Furthermore, the required data structure—balanced panels with consistent pre- and post-intervention periods—was frequently absent in available datasets, complicating direct application.", "conclusion": "While the DiD framework offers a powerful quasi-experimental design for evaluating adoption initiatives, its uncritical application in this context is problematic. Methodological rigour must be prioritised over the mere availability of panel data to ensure credible impact estimates.", "recommendations": "Future studies should incorporate pre-trend testing and robustness checks, such as event study designs or synthetic control methods. Investment in structured, high-frequency monitoring data is essential to build the evidence base required for effective industrial policy.", "key words": "process