Abstract
The risk of a child dying before completing five years of age is still highest in sub-Saharan Africa region. In this paper, we used the copula based dependence to investigate the association between the under-five mortality rate and Gross Domestic Product in Rwanda from 1981 to 2015. The copula has for a long time been recognized as a powerful tool for modeling dependence between two random variables. The Archimedean copulas were applied to capture the non-linearity in the dependence structure between those two vectors. Our findings showed that after 1994, the under-five mortality rate in Rwanda diminished steadily from 300 up to 42 per 1000 lives in 2015. Our analysis showed that under-five mortality rate is inversely proportional to the Gross Domestic Product. Unfortunately, it is not obvious to predict the future under-five mortality rate according to the Gross Domestic Product because it changes yearly according to the political measures of country. In this paper, we considered two Archimedean copulas namely Gumbel and Clayton.
Highlights
The risk of death of children under-5 years is still very high in sub-Saharan Africa region
Under-five mortality is still high in low and middle income countries; in this paper, we used a copula approach to measure the dependence between under-five mortality rate and gross domestic product (GDP) in order to investigate the level of effect of GDP to the mortality
In this article the Archimedean copulas were used for modelling the concordance measures: Kendall’s tau and spearman’s rho for mortality rate under-5 years in Rwanda in the period of 1981-2015
Summary
The risk of death of children under-5 years is still very high in sub-Saharan Africa region. Under-five mortality is still high in low and middle income countries; in this paper, we used a copula approach to measure the dependence between under-five mortality rate and gross domestic product (GDP) in order to investigate the level of effect of GDP to the mortality. The copula is powerful tool for dependency structure; it is a good approach for non-linearly correlated variables. The draw- back of linear correlation coefficients is that out of elliptical distributions, the usage may mislead to the good conclusion. In this article the Archimedean copulas were used for modelling the concordance measures: Kendall’s tau and spearman’s rho for mortality rate under-5 years in Rwanda in the period of 1981-2015
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have