{ "background": "Community health centres are pivotal for public health risk reduction in sub-Saharan Africa, yet robust methodological frameworks for evaluating their systemic performance are lacking. Existing assessments often fail to account for the hierarchical structure of health data, where patient outcomes are nested within facilities.", "purpose and objectives": "This case study presents a methodological evaluation of applying multilevel regression to measure risk reduction performance within community health centre systems. Its objective is to demonstrate the model's utility for isolating facility-level effects from individual patient characteristics.", "methodology": "We detail a methodological case study using anonymised longitudinal patient data from a network of centres. The core statistical model is a two-level random intercept logistic regression: $\\text{logit}(P(Y{ij}=1)) = \\beta0 + \\beta X{ij} + uj$, where $Y{ij}$ is a binary outcome for patient $i$ in centre $j$, $X{ij}$ are individual covariates, and $uj \\sim N(0, \\sigma^2u)$ is the centre-specific random effect. Inference was based on robust standard errors.", "findings": "The analysis quantified substantial variation in performance attributable to the centre level. The intra-class correlation coefficient was estimated at 0.18, indicating that 18% of the variance in patient outcomes was explained by differences between centres, after controlling for individual risk factors. This centre-level effect was statistically significant (p < 0.01).", "conclusion": "Multilevel modelling is a powerful methodological tool for health systems evaluation, effectively partitioning variance to identify facility-level performance disparities that aggregate metrics mask.", "recommendations": "Health ministries and researchers should adopt multilevel frameworks for routine health system evaluation. This approach should inform targeted resource allocation and quality improvement programmes for underperforming centres.", "key words": "health systems evaluation, multilevel modelling, random effects, primary healthcare, sub-Saharan Africa, methodological study", "contribution statement": "This paper provides a novel,