Modelling Spatial Patterns of Misaligned Disease Data: An Application on Measles Incidence in Namibia

Clinical Epidemiology and Global Health

D. Ntirampeba, I. Neema, LN. Kazembe


Quite often disease data are available in aggregated formats mostly to maintain confidentiality. This leads to a misalignment problem when the goal is to analyze risk at a different level of spatial resolution different from the original administrative level where data were available.


To estimate and map the risk of measles at a sub-region level in Namibia using data obtained at a regional level.


Using measles data from Namibia for the period 2005–2014, both multi-step and direct approaches were applied to correct for misalignment. Subsequently, ecological Bayesian regression models were fitted and compared.


Results show that the variables standardized birth rate, counts of measles cases for previous year, unemployment rate and proportion of vaccinated children against measles by age 12 months were significant determinants of measles risk. Constituencies having elevated measles risk were identified mostly in the northern corridor with Angola.


We recommend that relevant authorities should make geographical target intervention and redesign prevention and control strategies based on these findings.


Featured Country: Namibia

Scroll to Top