Authors
Joseph Larmarange, Centre Francais sur la Population et le Developpement (CEPED)
Roselyne Vallo, Université de Montpellier I
Seydou Yaro, Centre Muraz
Philippe Msellati, Institut de Recherche pour le Développement (IRD)
Nicolas Meda, Centre Muraz
Benoît Ferry, Centre Francais sur la Population et le Developpement (CEPED)
Abstract
For many countries, in particular in sub-Saharan Africa, Demographic and Health Surveys (DHS) are the only national source of data (depending of the subject). Several DHS collect latitude and longitude of surveyed clusters but the sampling method is not appropriate to derive local estimates : sample size is not large enough for a direct spatial interpolation. We develop in this paper a new approach for estimating a proportion for each sample cluster by aggregating data from neighbouring clusters. This estimated proportion can then be interpolated by kriging method. Estimation parameters were computed from 24500 survey simulations on a model country. This approach allows estimating regional trends of a phenomenon under the assumption that it is spatially continuous. The method was developed to map HIV prevalence in Burkina Faso and Cameroon at sub-national level but it can be applied to any other proportion. Our results will be compared with maps by DHS regions.