Publication Details

Amoako Johnson, F., Chandra, H., Brown, J. J. & Padmadas, S. S. 2010, 'District-level Estimates of Institutional Births in Ghana: Application of Small Area Estimation Technique Using Census and DHS Data', Journal of Official Statistics: an international quarterly, vol. 26, no. 2, pp. 341-359.


The Ghana Health Service functions under a decentralised approach; however, the lack of district level statistics implies that local authorities are faced with difficulties in making policy decisions without relevant statistics. The Ghanain Demographic and Health Surveys provide a range of invaluable data at the regional/national level; they cannot be used directly to produce reliable district-level estimates due to small sample sizes. This article uses small area estimation techniques to derive model-based district-level estimates of institutional births in Ghana by linking data from the 2003 GDHS and the 2000 Population and Housing Census. The models indicate considerable variability in the estimates, with institutional births ranging between 7% and 27% in the districts of the Northern region, compared to 78% and 85% in the districts of the Greater Accra Region. The diagnostic measures indicate that the model-based estimates are reliable and representative of the district to which they belong.