×

Extreme points of Lorenz and ROC curves with applications to inequality analysis. (English) Zbl 1492.91125

Summary: We find the extreme points of the set of convex functions \(\ell : [0, 1] \to [0, 1]\) with a fixed area and \(\ell(0) = 0\), \(\ell(1) = 1\). This collection is formed by Lorenz curves with a given value of their Gini index. The analogous set of concave functions can be viewed as receiver operating characteristic (ROC) curves. These functions are extensively used in economics (inequality and risk analysis) and machine learning (evaluation of the performance of binary classifiers). We also compute the maximal \(L^1\)-distance between two Lorenz (or ROC) curves with specified Gini coefficients. This result allows us to introduce a bidimensional index to compare two of such curves, in a more informative and insightful manner than with the usual unidimensional measures considered in the literature (Gini index or area under the ROC curve). The analysis of real income microdata illustrates the practical use of this proposed index in statistical inference.

MSC:

91B15 Welfare economics
91B82 Statistical methods; economic indices and measures

References:

[1] Aliprantis, C. D.; Border, K. C., Infinite Dimensional Analysis: A Hitchhiker’s Guide (2006), Springer · Zbl 1156.46001
[2] Alonso, L. E.; Fernández, C. J.; Ibáñez, R., “I think the middle class is disappearing”: crisis perceptions and consumption patterns in Spain, Int. J. Consum. Stud., 41, 389-396 (2017)
[3] Andreoli, F., Robust inference for inverse stochastic dominance, J. Bus. Econ. Stat., 36, 1, 146-159 (2018)
[4] Arnold, B. C.; Sarabia, J. M., Majorization and the Lorenz Order with Applications in Applied Mathematics and Economics (2018), Springer · Zbl 1397.62001
[5] Blavier, P., How did the great recession affect income inequality in Spain?, Econ. Sociol. Eur. Electron. Newsl., 19, 1, 7-14 (2017)
[6] Brezis, H., Functional Analysis, Sobolev Spaces and Partial Differential Equations (2011), Springer · Zbl 1220.46002
[7] de la Cal, J.; Cárcamo, J., Inverse stochastic dominance, majorization, and mean order statistics, J. Appl. Probab., 47, 1, 277-292 (2010) · Zbl 1200.62141
[8] Cowell, F., Measuring Inequality (2011), Oxford University Press
[9] Dentcheva, D.; Ruszczyński, A., Inverse stochastic dominance constraints and rank dependent expected utility theory, Math. Program., 108, 2, 297-311 (2006) · Zbl 1130.91327
[10] De Maio, F. G., Income inequality measures, J. Epidemiol. Community Health, 61, 849-852 (2007)
[11] The Economist, Lessons from Spain’s recovery after the euro crisis (26 Jul. 2018), Available:
[12] Efron, B., Bootstrap methods: another look at the jackknife, Ann. Stat., 7, 1-26 (1979) · Zbl 0406.62024
[13] Eliazar, I. I.; Sokolov, I. M., Measuring statistical evenness: a panoramic overview, Phys. A, Stat. Mech. Appl., 391, 4, 1323-1353 (2012)
[14] Evans, L. C.; Gariepy, R. F., Measure Theory and Fine Properties of Functions (1992), CRC Press · Zbl 0804.28001
[15] Fawcett, T., An introduction to ROC analysis, Pattern Recognit. Lett., 27, 8, 861-874 (2006)
[16] Getz, W. M.; Wilmers, C. C., A local nearest-neighbor convex-hull construction of home ranges and utilization distributions, Ecography, 27, 489-505 (2004)
[17] Hastie, T.; Tibshirani, R.; Friedman, J., The Elements of Statistical Learning: Data Mining, Inference and Prediction (2009), Springer: Springer New York · Zbl 1273.62005
[18] International Monetary Fund, Article IV Consultation-Press Release; Staff Report; and Statement by the Executive Director for Spain (6 Oct. 2017), Country Report No. 17/319
[19] International Monetary Fund, Article IV Consultation-Press Release; Staff Report; and Statement by the Executive Director for Spain (13 Nov. 2020), Country Report No. 2020/298
[20] Kleiber, C.; Kotz, S., Statistical Size Distributions in Economics and Actuarial Sciences, vol. 470 (2003), John Wiley & Sons · Zbl 1044.62014
[21] Leshno, M.; Levy, H., Preferred by “all” and preferred by “most” decision makers: almost stochastic dominance, Manag. Sci., 48, 8, 1074-1085 (2002) · Zbl 1232.90224
[22] Lloyd, C. J., Estimation of a convex ROC curve, Stat. Probab. Lett., 59, 1, 99-111 (2002) · Zbl 1056.62077
[23] Muliere, P.; Scarsini, M., A note on stochastic dominance and inequality measures, J. Econ. Theory, 49, 2, 314-323 (1989) · Zbl 0682.90029
[24] Parker, F. D., Integrals of inverse functions, Am. Math. Mon., 62, 6, 439-440 (1955)
[25] Phelps, R. R., Lectures on Choquet’s Theorem, Lecture Notes in Mathematics, vol. 1757 (2001), Springer · Zbl 0997.46005
[26] Pinelis, I., On the extreme points of moments sets, Math. Methods Oper. Res., 83, 3, 325-349 (2016) · Zbl 1351.49028
[27] Prendergast, L. A.; Staudte, R. G., A simple and effective inequality measure, Am. Stat., 72, 4, 328-343 (2018) · Zbl 07663957
[28] Shaked, M.; Shanthikumar, J. G., Stochastic Orders (2006), Springer
[29] Shorrocks, A. F.; Foster, J. E., Transfer sensitive inequality measures, Rev. Econ. Stud., 54, 3, 485-497 (1987) · Zbl 0624.90017
[30] Simon, B., Convexity (2011), Cambridge University Press · Zbl 1229.26003
[31] Vallender, S. S., Calculation of the Wasserstein distance between probability distributions on the line, Theory Probab. Appl., 18, 4, 784-786 (1974) · Zbl 0351.60009
[32] Villani, C., Optimal Transport: Old and New (2009), Springer · Zbl 1156.53003
[33] Winkler, G., Extreme points of moment sets, Math. Oper. Res., 13, 4, 581-587 (1988) · Zbl 0669.60009
[34] Wolfram Research, Mathematica (2012), Inc., Version 9.0, Champaign, IL
[35] Yitzhaki, S.; Schechtman, E., The Gini Methodology: A Primer on a Statistical Methodology (2012), Springer Science & Business Media · Zbl 1292.62013
[36] Zheng, B., Almost Lorenz dominance, Soc. Choice Welf., 51, 1, 51-63 (2018) · Zbl 1397.91506
[37] Zoli, C., Inverse stochastic dominance, inequality measurement and Gini indices, J. Econ., 77, 1, 119-161 (2002) · Zbl 1014.91079
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.