African Animal Health Research | 23 May 2011
Methodological Evaluation of Public Health Surveillance Systems in Kenya Using Multilevel Regression Analysis for Clinical Outcomes Assessment
M, w, i, h, a, k, i, K, i, n, y, u, a, ,, K, i, p, l, a, g, a, t, G, i, t, o, n, g, a, ,, N, g, u, g, i, O, t, i, e, n, o
Abstract
Public health surveillance systems in Kenya are essential for monitoring infectious diseases such as malaria and tuberculosis (TB). However, their effectiveness varies across different regions and levels of administration. A multilevel regression model will be employed to analyse data collected from various healthcare facilities in Kenya. The model will account for both fixed effects (e.g., facility-level characteristics) and random effects (e.g., regional variations). The analysis revealed that facility-level infrastructure significantly influenced clinical outcomes, with a moderate effect size. Our multilevel regression approach provides valuable insights into the performance of surveillance systems in Kenya, offering a refined method for future evaluations. Future studies should consider incorporating additional variables to enhance model accuracy and address potential biases. Treatment effect was estimated with $\text{logit}(p<em>i)=\beta</em>0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.