{ "background": "Access to safe drinking water remains a critical challenge in many regions, with the performance of installed treatment systems often poorly understood. Evaluating the real-world adoption and sustained use of such infrastructure is essential for effective engineering interventions and resource allocation.", "purpose and objectives": "This case study aims to develop and apply a robust quasi-experimental methodology to diagnose the causal impact of a large-scale water treatment programme on household adoption rates. It seeks to move beyond descriptive statistics to isolate the programme's effect from underlying trends.", "methodology": "A difference-in-differences (DiD) model is employed, comparing adoption trends in treatment villages (receiving new membrane filtration systems) with matched control villages over two survey rounds. The core model is specified as $Y{it} = \\beta0 + \\beta1 \\text{Treat}i + \\beta2 \\text{Post}t + \\delta (\\text{Treat}i \\times \\text{Post}t) + \\epsilon{it}$, where $Y{it}$ is the adoption rate. Inference is based on cluster-robust standard errors at the village level.", "findings": "The DiD estimator ($\\delta$) indicates a statistically significant positive effect of the new systems. The programme increased household adoption of treated water by 18.4 percentage points (95% CI: 12.1 to 24.7). However, the final adoption rate in treatment villages plateaued at approximately 65%, suggesting persistent behavioural or access barriers.", "conclusion": "The intervention successfully increased adoption, yet a substantial utilisation gap remains. The DiD approach provided a more rigorous assessment of the programme's impact than simple pre-post comparison, which was confounded by a secular upward trend in the control group.", "recommendations": "Future engineering programmes should integrate such diagnostic evaluation models from the design phase. Complementary soft engineering interventions, such as community mobilisation and maintenance training, are required to address the residual non-adoption gap identified.",