Abstract

Analysis of diarrhoea data in Malawi has been commonly done using classical methods. However, of late new approaches, such as Bayesian methods, have been introduced in literature. This study aimed at trying out new statistical techniques in comparison with the classical ways as well as finding out how each isolates dominant factors for a child‘s risk to diarrhoea. To isolate dominant factors, Logit, Poisson, and Bayesian models were fitted to 2006 Malawi Multiple Indicator Cluster Survey data, collected with an aim of estimating key indicators of women and child health per district. The comparison between Logit and Poisson models was done via chi-square‘s goodness-of-fit test. Confidence and Credible Intervals were used to compare Bayesian and Logit/Poisson model estimates. Modelling and inference in Bayesian method was done through MCMC techniques. The results showed agreement in directions of estimates from Bayesian and Poisson/Logit models, but Poisson provided better fit than Logit model. Further, all models identified child‘s age, breastfeeding status, region of stay and toilet-sharing status as significant factors for determining the child‘s risk. The models ruled out effects of mother‘s education, area of residence (rural or urban), and source of drinking water on the risk. But, Bayesian model proved significant closeness to lake/river factor, which was not the case with Poisson/ Logit model. The findings imply that classical and semiparametric models are equally helpful, while Poisson is better than Logit model when estimating the child‘s risk to diarrhoea.

More details

School	: School of Natural and Applied Sciences
Issued Date	: 2012

Download full document