Journal Article
Global inequality

Despite the growing interest in global inequality, assessing inequality trends is a major challenge because individual data on income or consumption is not often available. Nevertheless, the periodic release of certain summary statistics of the income distribution has become increasingly common. Hence, grouped data in form of income shares have been conventionally used to construct inequality trends based on lower bound approximations of inequality measures.

This approach introduces two potential sources of measurement error: first, these estimates are constructed under the assumption of equality of incomes within income shares; second, the highest income earners are not included in the household surveys from which grouped data is obtained.

In this paper, we propose to deploy a flexible parametric model, which addresses these two issues in order to obtain a reliable representation of the income distribution and accurate estimates of inequality measures. This methodology is used to estimate the recent evolution of global interpersonal inequality from 1990 to 2015 and to examine the effect of survey under-coverage of top incomes on the level and direction of global inequality.

Overall, we find that item non-response at the top of the distribution substantially biases global inequality estimates, but, more importantly, it might also affect the direction of the trends.