Multilevel Analysis of Determinants of Early Marriage Among Women in Ethiopia: Using Bayesian and Classical Approach

Negash, Moges

dc.contributor.author	Negash, Moges
dc.date.accessioned	2020-09-08T07:40:23Z
dc.date.available	2020-09-08T07:40:23Z
dc.date.issued	2020-09-07
dc.identifier.uri	http://hdl.handle.net/123456789/11191
dc.description.abstract	Abstract Early marriage is still widely exercised in many parts of the world chiefly in Latin America, the Caribbean, Southern Asia and countries of Africa. Ethiopia has one of the highest rates of early marriage in the world and Sub-Saharan Africa, ranking 18th globally. In Ethiopia the national prevalence of early marriage was 58%. Thus, this study was aimed to identify the determinants of early marriage among women in Ethiopia using Bayesian and classical approach. The data were extracted from the 2016 Ethiopia Demographic and Health Survey. The study included a sample from 9479 married women nested within eleven regions with age 15-49 years. The data were collected using two-stage cluster design that includes selections of enumeration area as first stage and selection of households as second stage. A two-stage model comparison was fitted to determine the individual and regional level factors associated with early marriage. Besides, this, the researcher has compared the Bayesian and classical multilevel logistic regression models. This study also revealed that the prevalence of early marriage among the women aged between 15 to 49 years in country was around 58.2%. For this study Bayesian random intercept multilevel model was found to be appropriate model in fitting the data suitably. The study, results revealed that the predictors such as place of residence, religion of woman, educational level of women, husband’s education level, respondents work status, wealth index and exposure to mass media and ethnicity were found to be significant predictors for early marriage among women. The Bayesian random intercept model also revealed that there was a significant variation in early marriage across regions of Ethiopia. The results showed that a random effects of religion, women and husband educational level of women is found to be significant in explaining the variation of early marriage across the regions of Ethiopia. As a result special attention require to be committed, in specifically to the regions’ access to education for young women to reduce early marriage and educating women through their religious leaders is also good means of raising the age at the first marriage. Especially it is advisable to Muslim religion leaders to delay early marriage of women for their followers by giving basic information regards to marriage and by developing the perception of women. Key words: MCMC, Early marriage, Multilevel model	en_US
dc.language.iso	en_US	en_US
dc.subject	Statistics	en_US
dc.title	Multilevel Analysis of Determinants of Early Marriage Among Women in Ethiopia: Using Bayesian and Classical Approach	en_US
dc.type	Thesis	en_US