Optimization of Gini Coefficient Affected by Imperfect Input Data

Abstract

Most indicators used for the determination of distributional effects of taxes or inequality of income distribution are based on the Gini coefficient and Lorenz curve to a substantial extent. Moreover, the potential of application of the Gini coefficient itself is much larger. However, the Lorenz curve and in particular the Gini coefficient need not present precise information on the income or wealth distribution in the society. The Gini coefficient values may be affected by the form of input data. We have ascertained that the level of the Gini coefficient distortion depends on the number of households included in the research while the income distribution in the sample is unequal. We have also defined the form of the Gini coefficient whose final value is cleaned from the mentioned influence of input data.