A Multilevel Regression Analysis for Cost-Effectiveness Diagnostics in Rwandan Manufacturing Systems

{ "background": "The drive for industrialisation in East Africa necessitates robust, context-specific tools for evaluating manufacturing efficiency. Existing cost-effectiveness diagnostics often fail to account for the hierarchical structure of plant data and regional operational heterogeneity, limiting their utility for strategic investment.", "purpose and objectives": "This study develops and validates a multilevel modelling framework to diagnose cost-effectiveness in manufacturing systems. The primary objective is to quantify the proportion of cost variance attributable to plant-level operational factors versus broader regional economic conditions.", "methodology": "A cross-sectional dataset from a stratified sample of manufacturing plants was analysed using a three-level random intercepts model. The core statistical model is specified as (Costijk) = \β0 + \β Xijk + uk + vjk + eijk, where i, j, and k index observations, plants, and regions, respectively. Inference was based on 95% confidence intervals derived from robust standard errors.", "findings": "Plant-level operational factors accounted for 68% of the variance in production costs, with regional economic infrastructure explaining a significant minority. A one-unit increase in the normalised maintenance schedule adherence score was associated with a 7.3% reduction in unit cost (95% CI: 5.1% to 9.5%).", "conclusion": "The multilevel regression approach provides a superior diagnostic tool by disentangling nested sources of cost variation, offering more actionable insights than conventional single-level analyses.", "recommendations": "Manufacturing policymakers and plant managers should adopt hierarchical modelling for capital allocation decisions. Investment should prioritise plant-level operational improvements, particularly predictive maintenance systems, while concurrently addressing regional infrastructure deficits.", "key words": "multilevel modelling, cost diagnostics, industrial efficiency, manufacturing systems, hierarchical data, East Africa", "contribution statement": "This paper presents a novel application of multilevel regression for manufacturing cost diagnostics, providing the first empirically derived variance decomposition for production costs