Demographic and Health surveys (DHS) data measuring the rate of stunting in children under age 5 were used to predict high spatial resolution gender disaggregated maps, at unobserved location in Nigeria, Kenya and Bangladesh, using predictive modelling techniques. Bayesian geostatistical and machine learning modelling methods (Artificial neural networks) are used to take advantage of the fact that many indicators related to population health and development are correlated to environmental or sociological factors, many of which are available nowadays as gridded spatial datasets.
The outputs consist of high-resolution maps (1x1 km) of stunting in boys and girls in Nigeria, Kenya and Bangladesh together with estimates of mapping uncertainty. Quantify the distribution of gender disaggregated childhood stunting in low- or medium-low- income countries is valuable to adequately inform policy-makers and decision-makers for promoting any initiative aimed at making advances towards reducing stunting and achieving gender equality.
Andy Tatem, Claudio Bosco
WorldPop, Geography and Environment University of Southampton A.J.Tatem@soton.ac.uk, C.Bosco@soton.ac.uk (023) 8059 2636
UN Foundation, Data2x program