Public health surveillance systems in Kenya are critical for monitoring infectious diseases such as malaria and tuberculosis (TB). However, their effectiveness varies across different regions. Multilevel regression models were employed to analyse data from multiple sources, including healthcare facilities and community surveys. Data was collected over a five-year period across various regions in Kenya. Uncertainty in model estimates was quantified using robust standard errors. The analysis revealed significant differences in surveillance system performance between urban and rural areas (p < 0.05). Cost-effectiveness varied by region, with an estimated cost-saving potential of $12 per capita annually for the most effective systems. This study provides a comprehensive evaluation of public health surveillance systems in Kenya, highlighting regional disparities and economic benefits. Policy recommendations include targeted investments in rural areas to enhance system performance and overall cost-effectiveness. Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.