A Robust Gini Type-Index Better Detects Shifts in the Income Distribution: A Reanalysis of Income Inequality in the United States from 1967-2011

Abstract

The increase in income inequality in many countries, apparently due to a greater relative increase in upper incomes, has become a public policy concern. This paper shows that the standard Gini index underestimates the rate of increase in inequality because a shift of income towards the top incomes increases both its numerator and denominator. A modified index (G2), obtain by replacing the mean in the denominator by the median indicates that income inequality in the United States grew at double the rate of the Gini index from 1967 to 2011. The analysis adjusts for the effect of the changes made to the survey in 1994. The index G2 is readily computed from the mean, median and Gini index, routinely published by the U.S. Census Bureau and other national statistical agencies. While other indices give greater weight to the upper end of the income distribution, they must be calculated from micro-data. The large sample properties of the empirical estimator of G2 are obtained. While the limitations of the index G2 for some analytic purposes are noted, it is an easily calculated summary descriptive measure that is more sensitive to important changes in the income distribution than the Gini index.