bensonboro/child_mortality_determinants_in_Uganda

In this project, I analyzed the determinants of child mortality in Uganda. I obtained the data from the 2022 Demographic and Health Survey. Throughout the analysis, DHS survey weights were applied to produce descriptive, bivariate, and multivariate analysis using Stata and R. # 1. Project title Determinants of Child Mortality: Evdence from the 2022 Uganda Demographic and Health Survey (DHS) # 2. Research question Does child, maternal, and socioeconomic factors predict child survival in Uganda? # 4. Data source I obtained a sample size of 1434 children from the Kid's Record file of the 2022 Uganda Demographic and Health Survey (DHS). The data was requested from and provided by the Uganda Bureau of Statistics. After obtaining the dataset, I extracted the key child, maternal, and household characteristics to analyse. These variables included: Maternal education, household wealth, birth interval, maternal age, total number of children born, water sources, place of residence, and region, among others. ## Outcome variable - Child survival status, that is, whether a child died or not before the age of five ## Explanatory variables - Maternal education - Household wealth - birth interval - maternal age - total number of children born - water sources - place of residence - region # 5. Methodology First, I utilised descriptive data analysis to understand the overall nature of child mortality in Uganda. In this phase, I produced descriptive tables and figures to present the data. Secondly, I conducted a bivariate analysis to understand the relationship between child mortality and the explanatory variables. Finally, I conducted a multivariate logistic regression to examine the key determinants of child mortality, taking into account other factors. The analysis accounted for the DHS sampling design through clustering, stratification, and probability weights. Results are reported as adjusted odds ratio with 95% confidence intervals, and statistical significance was assessed at the 5% level. The analysis was done using R and Stata. R was particularly used for data extraction, descriptive analysis, and graphical analysis. Stata on the other hand was used for data cleaning, variable construction, and survey-weighted logistic analysis. # 6. Key fin …