Statistical models to understand factors associated with under-five child mortality in Tanzania.
Loading...
Date
2016
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The risk or probability of dying between birth and five years of age expressed per 1000
live births is known as Under-five mortality. The well-being of a child reflects household,
community and national involvement on family health. This will have an immense future
contribution towards the development of a country. Globally, a substantial progress in
improving child survival since 1990 has been made. The decline globally in under-five
mortality from approximately 12.7 million in 1990 to approximately 6.3 million in 2013
had been observed. Notably, all regions except Sub-Saharan Africa, Central Asia, Southern
Asia and Oceania had reduced the rate by 52% or more in 2013. This study aims to
identify factors that are associated with the under-five mortality in Tanzania. In order
to robustly identify these factors, the study utilized different statistical models that accommodate
a response which is dichotomous. Models studied include Logistic Regression
(LR), Survey Logistic Regression (SLR), Generalized Linear Mixed Model (GLMM) and
Generalized Additive Model (GAM). The result revealed that HIV status of the mother
is associated with the under-five mortality. Furthermore, the results revealed that childbirth
order number, breastfeeding and a total number of children alive affects the survival
status of the child. The study shows that there is a need to intensify child health interventions
to reduce the under-five mortality rate even more and to be in line with the
millennium development goal 4(MDG4).
Description
Master of Science in Statistics. University of KwaZulu-Natal, Pietermaritzburg 2016.
Keywords
Children -- Mortality -- Statistics., Parameter estimation., Theses -- Statistics., Under-five mortality.