Abstract
Different methods for describing health disparities in the distributions of continuous measured health-related variables among groups provide more insight into the nature and impact of the disparities than comparing measures of central tendency. Transformations of the Lorenz curve and analogues of the Gini index used in the analysis of income inequality are adapted to provide graphical and analytical measures of health disparities. Akin to the classical Peters-Belson regression method for partitioning a disparity into a component explained by group differences in a set of covariates and an unexplained component, a new modified Lorenz curve is proposed. The estimation of these curves/measures is adapted for data obtained from surveys with complex sample weighted designs. The statistical properties of sample weighted estimators of the proposed measures and their bootstrap variances are explored through simulation studies. Applications are demonstrated using BMI and blood lead levels among race/ethnic groups of adult females and children, respectively, from the 2013-2018 and 1988-1994 US National Health and Nutrition Examination Surveys. Another application examines disparities in distance to nearest acute care hospital among census blocks in the US state of New York grouped by their level of urbanicity using US census data and the American Hospital Association survey.