Journal Design Engineering Masthead
African Civil Engineering Journal | 10 December 2016

A Difference-in-Differences Model for the Cost-Effectiveness Evaluation of Process-Control System Methodologies in South Africa

T, h, a, n, d, i, w, e, N, k, o, s, i, ,, P, i, e, t, e, r, v, a, n, d, e, r, M, e, r, w, e, ,, K, a, g, i, s, o, N, a, i, d, o, o
DOI: https://doi.org/10.5281/zenodo.18965222
Difference-in-differencesCost-effectivenessProcess ControlProject Evaluation
A quasi-experimental DiD model isolates the causal effect of a new process-control methodology.
Empirical analysis shows an 18.2% reduction in the cost-efficiency ratio attributable to the intervention.
The framework moves evaluation beyond anecdotal evidence to robust, quantitative assessment.
Findings support adopting evidence-based evaluation for major engineering procurement decisions.

Abstract

{ "background": "The adoption of advanced process-control system methodologies in engineering projects represents a significant capital investment. Robust, quantitative frameworks for evaluating their cost-effectiveness within specific operational contexts, such as South Africa, are lacking, leading to reliance on anecdotal or theoretical assessments.", "purpose and objectives": "This case study aims to develop and apply a quasi-experimental difference-in-differences (DiD) model to empirically measure the net cost-effectiveness of implementing a new statistical process control methodology in a local civil engineering context, isolating its causal effect from other confounding factors.", "methodology": "A longitudinal case study was conducted, analysing cost and performance data from two comparable water treatment plant upgrade projects—one implementing the new methodology (treatment group) and one using conventional practices (control group). The core DiD estimator 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 $Y{it}$ is the cost-efficiency ratio. Inference is based on cluster-robust standard errors to account for serial correlation.", "findings": "The DiD estimate ($\\delta$) indicates a statistically significant reduction in the cost-efficiency ratio of 18.2% (95% CI: 12.5% to 23.9%) attributable to the new methodology. This represents a substantial improvement in cost-effectiveness, driven primarily by a reduction in rework and material waste.", "conclusion": "The applied DiD model provides a rigorous, evidence-based framework for evaluating process-control interventions, demonstrating the tangible cost benefits of the specific methodology in the studied context.", "recommendations": "Project managers and civil engineering firms should adopt quasi-experimental evaluation frameworks like DiD for major procurement and methodology decisions. Further research should apply this model across different engineering sectors and project scales.", "key words": "