African Technology and Development (Interdisciplinary - | 02 October 2001
Multilevel Regression Analysis for Measuring System Reliability in Process-Control Systems Across Kenya's Multiscale Governance Contexts,
M, a, r, k, K, i, n, y, a, n, j, u, i, ,, O, s, c, a, r, O, l, u, o, c, h, a, k, o, n, g
Abstract
This study examines the reliability of process-control systems in Kenya's multiscale governance contexts. Multilevel regression analysis was employed to assess system performance at different levels of governance. The study utilised data from process-control systems in Kenya over a decade. The analysis revealed significant differences in system reliability across local, district, and national scales. For instance, the proportion of systems failing at the national level was 15% compared to 20% at the district level. Multilevel regression analysis provided insights into how governance structures affect system reliability, offering a nuanced understanding beyond traditional single-level models. Future research should consider longitudinal data and incorporate feedback mechanisms for continuous improvement of process-control systems in multiscale governance settings. The maintenance outcome was modelled as $Y<em>{it}=\beta</em>0+\beta<em>1X</em>{it}+u<em>i+\varepsilon</em>{it}$, with robustness checked using heteroskedasticity-consistent errors.