Geographical Variations and Associated Factors of Timely Vaccination Status Among Children in Somalia: An Application of Spatial and Multilevel Analysis

Background Vaccinating children is an important public health measure. Coverage in Somalia, however, remains uneven. To plan targeted treatments, it is essential to understand both the factors that influence vaccination and the location where it occurs. Methods This study analyzed data from the Somali Health and Demographic Survey (SHDS 2020) and employed multilevel logistic regression to examine individual and community-level factors influencing children's vaccination status. We used AIC, BIC, log-likelihood, and ICC values to compare the models' fit. Spatial clustering was assessed using Global Moran’s I, Local Moran’s I, and Getis-Ord Gi* statistics. Results Among 5,732 children, only 32.5% were fully vaccinated. The lowest coverage was observed among those under one year of age (24.1%). Maternal healthcare utilization was strongly associated with vaccination: children whose mothers had four or more ANC visits had more than three times the odds of being vaccinated (AOR = 3.25, 95% CI: 2.61–4.05) compared to those with no visits. Higher maternal education and urban residence were significant predictors, whereas children from nomadic households exhibited markedly lower odds (AOR = 4.29, 95% CI: 3.21–5.75). Spatial analysis revealed significant clustering (Global Moran’s I = 0.312, p < 0.01), with “hot spots” of high vaccination in Jubbada Hoose, Gedo, Bay, and Bakool, and “cold spots” in Sanaag, Togdheer, and Woqooyi Galbeed. Conclusion Childhood vaccination rates in Somalia remain low and are spatially clustered. Strengthening maternal health services, addressing nomadic populations, and prioritizing northern regions with persistently low immunization coverage are essential to achieving nationwide equity.