Copula-based estimation of health inequality measures

Abstract This paper aims to utilize bivariate copulas for deriving estimators of the health concentration curve and Gini coefficient for health distribution. We highlight the importance of expressing health inequality measures in terms of bivariate copulas, which we in turn use to build copula-based semi- and nonparametric estimators of the above measures. Subsequently, we investigate the asymptotic properties of these estimators, establishing their consistency, and asymptotic normality. We provide formulas for their variances, facilitating the construction of confidence intervals and tests for the health concentration curve and Gini health coefficient with respect to a given socioeconomic variable. Through a Monte–Carlo simulation exercise, we demonstrate the superior performance of the semiparametric estimator over the smoothed nonparametric estimator, with the latter outperforming the empirical estimator in terms of Mean Squared Error. Additionally, an extensive empirical study applies our estimators, revealing that inequalities in US states’ socioeconomic variables, such as income/poverty and race, contribute to observed disparities in COVID-19 infections and deaths in the U.S.