{ "background": "Community health centres are pivotal to primary care delivery in Kenya, yet methodological rigour in evaluating their clinical outcomes is inconsistent. Multilevel regression modelling is increasingly employed to account for the hierarchical structure of health data, but its application and reporting standards require systematic assessment.", "purpose and objectives": "This systematic review aims to critically evaluate the methodological application of multilevel regression analyses in studies measuring clinical outcomes within Kenyan community health centres, identifying common practices, strengths, and limitations.", "methodology": "A systematic search of multiple electronic databases was conducted for peer-reviewed articles. Studies were screened against pre-defined eligibility criteria, with data extracted on model specification, variable selection, and statistical reporting. Quality appraisal used a tailored checklist for multilevel modelling studies.", "findings": "Of the 27 included studies, a predominant methodological weakness was the failure to report intra-class correlation coefficients (ICC) to justify the use of multilevel models; this omission occurred in 63% of articles. The most frequently used model was a two-level random intercept logistic regression, expressed as $\\logit(p{ij}) = \\beta{0} + \\beta X{ij} + u{0j}$, where $u{0j} \\sim N(0, \\sigma{u0}^{2})$. Uncertainty was often poorly characterised, with only 41% reporting confidence intervals for variance components.", "conclusion": "The application of multilevel regression in this context is methodologically heterogeneous, with significant gaps in reporting that undermine the interpretability and reproducibility of findings on health centre effectiveness.", "recommendations": "Future research must adhere to established reporting guidelines for multilevel models, explicitly justify model choice with metrics like the ICC, and comprehensively report measures of uncertainty for all estimated parameters.", "key words": "health systems research, hierarchical linear models, primary health care, statistical reporting, sub-Saharan Africa", "contribution statement": "This review provides the first methodological synthesis and quality assessment of multilevel modelling practices for community health centre