Community health centres are a cornerstone of primary healthcare delivery in Kenya, yet systematic, longitudinal analysis of their operational efficiency is lacking. Existing evaluations often rely on cross-sectional data, which fails to capture dynamic performance changes and unobserved heterogeneity. This brief report aims to methodologically evaluate panel-data estimation techniques for measuring longitudinal efficiency gains within these centres. The objective is to identify a robust model that accounts for centre-specific effects and time-varying inefficiencies. We employ a true fixed-effects stochastic frontier model, $\ln y_{it} = \alpha_i + \beta'x_{it} + v_{it} - u_{it}$, where $u_{it} \sim N^+(\mu, \sigma_u^2)$, to analyse a constructed panel dataset. Model robustness was assessed using bootstrapped standard errors. The methodological evaluation indicates that failing to control for time-invariant heterogeneity biases efficiency estimates upwards by approximately 15-20%. The preferred model shows a statistically significant annual efficiency growth rate of 1.8% (95% CI: 1.2, 2.4) across the study period. Panel-data methods, specifically stochastic frontier analysis with fixed effects, are crucial for obtaining unbiased estimates of efficiency in community health systems. The application reveals consistent, though modest, long-term gains. Future research and national monitoring systems should adopt panel-data frameworks for performance assessment. Policymakers should prioritise investments that address the persistent, centre-specific inefficiencies identified. stochastic frontier analysis, health systems efficiency, panel data, primary healthcare, Kenya This report provides a novel methodological framework for longitudinal health system efficiency analysis in a low-resource setting, demonstrating the critical importance of modelling unobserved heterogeneity.