Water treatment facilities in Kenya are critical for ensuring safe drinking water, yet their performance varies significantly across different regions and socioeconomic groups. This study employs multilevel regression analysis to examine the impact of socio-economic status (SES) on water quality outcomes, utilising data from a national survey conducted in Kenya. The multilevel regression model reveals that SES has a significant moderating effect on treatment facility performance, with lower-income areas showing higher variability in treated water quality. Multilevel regression analysis offers a robust framework for understanding the complex interplay between socio-economic factors and water safety measures. Investment strategies should consider local SES patterns to optimise resource allocation for water treatment facilities, particularly in underserved regions. The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.