p-med/DHS-Data-Preparation-with-R

A comprehensive R script for processing and aggregating Demographic and Health Surveys (DHS) data from Mozambique's 2022 survey to cluster-level indicators suitable for spatial analysis and modeling. # Mozambique DHS 2022 Data Processing Pipeline A comprehensive R script for processing and aggregating Demographic and Health Surveys (DHS) data from Mozambique's 2022 survey to cluster-level indicators suitable for spatial analysis and modeling. ## Overview This script transforms individual and household-level DHS survey data into cluster-level aggregated indicators, enabling spatial analysis of health and demographic outcomes across Mozambique. The pipeline handles complex survey structures, applies proper weighting, and produces analysis-ready datasets with geographic coordinates. ## Features - **Multi-Module Integration**: Merges data from 13+ DHS modules (household, women, men, children, geographic) - **Standardized Indicators**: Calculates internationally comparable health and demographic indicators following DHS methodology - **Survey Weights**: Properly applies household and individual sampling weights for representative estimates - **Spatial Integration**: Includes cluster coordinates for GIS analysis and mapping - **Reproducible Pipeline**: Clear documentation and modular structure for transparency and replication ## Calculated Indicators ### Maternal and Reproductive Health - Women married by age 15 and 18 (ages 20-24) - Age at first birth (women 20-24, 25-29) - Skilled delivery assistance - Facility-based deliveries ### Child Health and Nutrition - Child stunting prevalence (height-for-age z-score < -2 SD) - Birth registration (children under 5) ### Literacy - Women's literacy rates (ages 15-49) - Men's literacy rates (ages 15-49) ### Gender-Based Violence - Physical, sexual, and emotional violence by intimate partners (past 12 months) - Composite indicator for any violence ### Family Planning - Current use of any contraceptive method ## Requirements ### R Packages ```r tidyverse # Data manipulation and visualization haven # DHS labeled variables labelled # Variable labeling expss # Tables with labeled data openx …