Some features of a new measure of income inequality based on the ratios between lower and upper medians

Document Type : Research Paper

Authors
1 Department of statistics, Payame Noor University, Tehran, Iran.
2 Department of Statistics, Payame Noor University, Tehran, Iran
Abstract
This paper introduces a median‑based measure of income inequality, defined as the ratio between the lower and upper medians of the income distribution. The index is defined pointwise, and its corresponding inequality curve is presented. We examine the essential properties of the index, including normalization, scale invariance, location sensitivity, and the Pigou–Dalton transfer principle. The behavior of the inequality curve is investigated within common parametric income models. A suitable estimator is proposed, and its strong consistency and asymptotic normality are established. Additionally, a stochastic order based on the proposed curve is defined and studied. Simulation studies show that the proposed estimator performs competitively compared to the Gini coefficient in terms of bias, mean squared error, and coverage probabilities. Finally, the measure is applied to real-household income data, illustrating its practical usefulness.
Keywords
Subjects

[1] A. Arcagni and F. Porro, The graphical representation of inequality, Revista Colombiana de Estadistica 37 (2014), no. 1, 419–436.
[2] B. C. Arnold, On zenga and bonferroni curves, Metron 73 (2015), no. 1, 25–30.
[3] C. E. Bonferroni, Elementi di statistica generale, Università commerciale L. Bocconi, 1941.
[4] H. A. David and H. N. Nagaraja, Order statistics, John Wiley and Sons, 2004.
[5] R. Davidson, Reliable inference for the gini index, Journal of Econometrics 150 (2009), 30–40.
[6] Y. Davydov and F. Greselin, Inferential results for a new measure of inequality, The Econometrics Journal 22 (2019), 153–172.
[7] J. L. Gastwirth, Median-based measures of inequality: Reassessing the increase in income inequality in the u. s. and sweden, Statistical Journal of the IAOS 30 (2014), 311–320.
[8] F. Greselin, L. Pasquazzi, and R. Zitikis, Contrasting the gini and zenga indices of economic inequality, Journal of Applied Statistics 40 (2013), 282–297.
[9] C. Kleiber and S. Kotz, Statistical size distributions in economics and actuarial sciences, John Wiley and Sons, Hoboken, New Jersey, 2003.
[10] M. O. Lorenz, Methods of measuring the concentration of wealth, Journal of the American Statistical Association 9 (1905), no. 70, 209–219.
[11] J. B. McDonald, Some generalized functions for the size distribution of income, Econometrica 52 (1984), 647–663.
[12] J. A. Mills and S. Zandvakili, Statistical inference via bootstrapping for measures of inequality, Journal of Applied Econometrics 12 (1997), 133–150.
[13] S. Mirzaei, G. R. Mohtashami Borzadaran, M. Amini, and H. Jabbari, Two competitor inequality indices in burr xii distribution, International Journal of Statistics and Economics 18 (2017).
[14] M. Polisicchio and F. Porro, A comparison between lorenz L(p) curve and zenga I(p) curve, Statistica Applicata 21 (2011), no. 3–4, 289–301.
[15] J. M. Sarabia, Parametric lorenz curves: Models and applications, Modeling Income Distributions and Lorenz Curves, Springer, New York, 2008, pp. 167–190.
[16] R. J. Serfling, Approximation theorems of mathematical statistics, John Wiley and Sons, 2009.
[17] A. W. van der Vaart, Asymptotic statistics, Cambridge University Press, 2000.
[18] M. Zenga, Inequality curve and inequality index based on the ratios between lower and upper arithmetic means, Statistica Applicazioni 5 (2007), no. 1, 3–28.
Volume 17, Issue 9
September 2026
Pages 31-52

  • Receive Date 28 January 2025
  • Revise Date 09 September 2026
  • Accept Date 16 September 2026