WITHDRAWN: An Investigation of Spatial Variation of Childhood Disease in India: A Bayesian Semiparametric Approach
Awdhesh Yadav, International Institute for Population Sciences, Mumbai, India
Keywords: Child morbidity, developing countries, geoadditive regression, India
Although diarrhea and malaria are the leading causes of child mortality and morbidity in developing countries, few studies have examined the pattern and determinants of these ailments. The purpose of this paper is to examine the relative contribution of a wide range of factors, specifically spatial effects to the prevalence of child morbidity (diarrhea, fever, & ARI). The data used in the analysis were taken from the third round of the National Family Health Survey (NFHS-3, 2005-06). We highlighted the inequalities in child health by mapping the residual state spatial effect using a geo-additive logit model. These models allow us to analyze usual linear effects of covariates, nonlinear effect of continuous covariates, and regional effects within a unified semiparametric Bayesian framework for modelling and inference. A high prevalence of diarrhea, fever, and acute respiratory is observed in the eastern, central, and northern states, while lower prevalence is observed in southern states followed by western states. In addition, children who are underweight and those from the poorest quintile have significantly higher association with diarrhea.