Geo-Additive Models of Childhood Undernutrition in Three Sub-Saharan African Countries
University of Munich SFB 386 Working Paper No. 287
30 Pages Posted: 19 Sep 2002
Date Written: July 2002
We investigate the geographical and socioeconomic determinants of childhood undernutrition in Malawi, Tanzania, and Zambia, three neighboring countries in Southern Africa using the 1992 Demographic and Health Surveys. We estimate models of undernutrition jointly for the three countries to explore regional patterns of undernutrition that transcend boundaries, while allowing for country-specific interactions.
We use semiparamtetric models to flexibly model the effects of selected socioeconomic covariates and spatial effects. Our spatial analysis is based on a flexible geo-additive model using the district as the geographic unit of analysis, which allows to separate smooth structured spatial effects from random effects. Inference is fully Bayesian and uses recent Markov Chain Monte Carlo techniques.
While the socioeconomic determinants generally confirm what is known in the literature, we find important non-linear effects of some covariates. Also, we find distinct residual spatial patterns that are not explained by the socioeconomic determinants. In Particular, there appears to be a belt running from Southern Tanzania to Northeastern Zambia which exhibits much worse undernutrition, even after controlling for socioecononomic effects. These effects do transcend borders, but to a varying degree.
These findings have important implications for targeting policy as well as the search for left-out variables that might account for these residual spatial patterns.
Keywords: Sub-Saharan Africa, Geo-Additive Models, Undernutrition, Spatial Analysis, Semiparametric Bayesian Analysis
JEL Classification: I12, J13, O12, O15
Suggested Citation: Suggested Citation