2018/04/23 by Antonio Pedro Ramos, Ramos, Antonio P., Robert E. Weiss +1
Health Professions · Medicine · Nursing · #Applications (stat.AP) #Child Nutrition and Water Access #FOS: Computer and information sciences #Global Health Care Issues #Global Maternal and Child Health
paper · pdf · doi:10.48550/arxiv.1804.08570
openalex publication_date 2018/04/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Most studies on inequality in infant and child mortality compare average\nmortality rates between large groups of births, for example, comparing births\nfrom different countries, income groups, ethnicities, or different times. These\nstudies do not measure within-group disparities. The few studies that have\nmeasured within-group variability in infant and child mortality have used tools\nfrom the income inequality literature, such as Gini indices. We show that the\nlatter are inappropriate for infant and child mortality. We develop novel tools\nthat are appropriate for analyzing infant and child mortality inequality,\nincluding inequality measures, covariate adjustments, and ANOVA methods. We\nillustrate how to handle uncertainty about complex inference targets, including\nensembles of probabilities and kernel density estimates. We illustrate our\nmethodology using a large data set from India, where we estimate infant and\nchild mortality risk for over 400,000 births using a Bayesian hierarchical\nmodel. We show that most of the variance in mortality risk exists within groups\nof births, not between them, and thus that within-group mortality needs to be\ntaken into account when assessing inequality in infant and child mortality. Our\napproach has broad applicability to many health indicators.\n