Abstract
Gini’s mean difference (GMD) as a measure of variability has been known for over a century. It has more than 14 alternative representations. Some of them hold only for continuous distributions while others hold only for nonnegative variables. It seems that the richness of alternative representations and the need to distinguish among definitions that hold for different types of distributions are the main causes for its sporadic reappearances in the statistics and economics literature as well as in other areas of research. An exception is the area of income inequality, where it is holding the position as the most popular measure of inequality. GMD was “rediscovered” several times (see, for example, Chambers 6; Quiggin, 2007; David, 1968; Jaeckel, 1972; Jurečková, 1969; Olkin Yitzhaki, 1992; Kőszegi Rabin, 2007; Simpson, 1949) and has been used by investigators who did not know that they were using a statistic which was a version of the GMD. This is unfortunate, because by recognizing the fact that a GMD is being used the researcher could save time and research effort and use the already known properties of GMD.
This chapter is based on Yitzhaki (1998) and Yitzhaki (2003).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
For a description of its early development see Dalton (1920), Gini (1921, 1936), David (1981, p. 192), and several entries in Harter (1978). Unfortunately we are unable to survey the Italian literature which includes, among others, several papers by Gini, Galvani, and Castellano. A survey on those contributions can be found in Wold (1935). An additional comprehensive survey of this literature can be found in Giorgi (1990, 1993). See Yntema (1933) on the debate between Dalton and Gini concerning the relevant approach to inequality measurement.
- 2.
- 3.
For the use of the GMD in categorical data see the bibliography in Dennis, Patil, Rossi, Stehman, and Taille (1979) and Rao (1982) in biology, Lieberson (1969) in sociology, Bachi (1956) in linguistic homogeneity, and Gibbs and Martin (1962) for industry diversification. Burrell (2006) uses it in informetrics, while Druckman and Jackson (2008) use it in resource usage, Puyenbroeck (2008) uses it in political science while Portnov and Felsenstein (2010) in regional diversity.
- 4.
One way of writing the Gini is based on vectors and matrices. This form is clearly restricted to discrete variables and hence it is not covered in this book. For a description of the method see Silber (1989).
- 5.
See also Pyatt (1976) for an interesting interpretation based on a view of the Gini as the equilibrium of a game.
- 6.
The GMD is based on the difference of two such formulae, so this restriction on the range (to be bounded from below) does not affect the GMD. See Dorfman (1979).
- 7.
This formula, which is a special case of the statistic suggested by Cramer, plays an important role in his composition of elementary errors although it seems that he did not identify the implied GMD (see Cramer, 1928, pp. 144–147). Von Mises (1931) made an independent equivalent suggestion and developed additional properties of the statistic. Smirnov (1937) modified the statistic to be
\( {{\text{w}}^{{2}}} = {\text{n}}\int {{{\left[ {{{\text{F}}_{\rm{n}}}\left( {\text{x}} \right) - {\text{F}}\left( {\text{x}} \right)} \right]}^{{2}}}{\text{dF}}\left( {\text{x}} \right)} \).
Changing the integration from dx to dF(x) eliminates the connection to the GMD and creates a distribution-free statistic. The above description of the non-English literature is based on the excellent review in Darling (1957). Further insight about the connection between the Cramér–Von Mises test can be found in Baker (1997) which also corrects for the discrepancy in calculating the GMD in discrete distributions.
- 8.
This “duality” resembles the alternative approach to the expected utility theory as suggested by Yaari (1988) and others. While expected utility theory is linear in the probabilities and nonlinear in the income, Yaari’s approach is linear in the income and nonlinear in the probabilities. In this sense, one can argue that the relationship between “dual” approach and the GMD resembles the relationship between expected utility theory and the variance. Both indices can be used to construct a specific utility function for the appropriate approach (the quadratic utility function is based on the mean and the variance while the mean minus the GMD is a specific utility function of the dual approach).
- 9.
Wold (1935) used a slightly different presentation, based on Stieltjes integrals.
- 10.
See Lerman and Yitzhaki (1984) for the derivation and interpretation of the formula, see Jenkins (1988) and Milanovic (1997) on actual calculations using available software, and see Lerman and Yitzhaki (1989) on using this equation to calculate the GMD in stratified samples. As far as we know, Stuart (1954) was the first to notice that the GMD can be written as a covariance. However, his findings were confined to normal distributions. Pyatt, Chen and Fei (1980) also write the GMD as a covariance. Sen (1973) uses the covariance formula for the Gini, but without noticing that he is dealing with a covariance. Hart (1975) argues that the moment-generating function was at the heart of the debate between Corrado Gini and the western statisticians. Hence, it is a bit ironic to find that one can write the GMD as some kind of a central moment.
- 11.
The term “generalized Lorenz curve” (GLC) was coined by Shorrocks (1983). Lambert and Aronson (1993) give an excellent description of the properties of GLC. However, it seems that the term “absolute” is more intuitive because it distinguishes the absolute curve from the relative one. Hart (1975) presents inequality indices in terms of the distribution of first moments, which is related to the GLC.
- 12.
In the case of the GMD, the weights are not functions of Δxk so that it is reasonable to refer to them as weights. In the case of the variance, the “weights” are also functions of Δxk which makes the reference to them as weights to be incorrect. We refer to them as weights in order to compare with the GMD. See Yitzhaki (1996).
- 13.
References
Bachi, R. (1956). A statistical analysis of the revival of Hebrew in Israel. Scripta Hierosolymitana, 3, 179–247.
Baker, R. D. (1997). A new perspective on the Cramer-Von Mises test. Nonparametric Statistics, 7, 255–277.
Burrell, Q. L. (2006). Measuring concentration within and co-concentration between informetric distributions: An empirical study. Scientometrics, 68(3), 441–456.
Ceriani, L., & Verme, P. (2011). The origins of the Gini index: Extracts from Variabilità e Mutabilità (1912) by Corrado Gini. Journal of Economic Inequality. Forthcoming.
Cerone, P., & Dragomir, S. S. (2005). Bounds for the Gini mean difference via the Sonin identity. Computers and Mathematics with Applications, 50, 599–609.
Cerone, P., & Dragomir, S. S. (2006). Bounds for the Gini mean difference of an empirical distribution. Applied Mathematics Letters, 19, 283–293.
Chambers, R. G., & Quiggin, J. (2007). Dual approaches to the analysis of risk aversion. Economica, 74, 189–213.
Cramer, H. (1928). On the composition of elementary errors (Second paper: Statistical applications). Skandinavisk Aktuareitidskrift, 11, 141–180.
Dalton, H. (1949). The measurement of the inequality of income. Economic Journal, 1920(30), 348–361 [Reprinted in the appendix to his the inequality of income. London: Routledge & Kegan Paul LTD.].
Daniels, H. E. (1944). The relation between measures of correlation in the universe of sample permutation. Biometrika, 33, 129–135.
Daniels, H. E. (1948). A property of rank correlation. Biometrika, 35, 416–417.
Darling, D. A. (1957). The Kolmogorov-Smirnov, Cramer-Von Mises tests. Annals of Mathematical Statistics, 28, 823–838.
David, H. A. (1968). Gin’is mean difference rediscovered. Biometrika, 55, 573–575.
David, H. A. (1981). Order statistics (2nd ed.). New York: John Wiley & Sons.
Deaton, A. (1979). The distance function in consumer behaviour with applications to index numbers and optimal taxation. The Review of Economic Studies, 46(3 (July)), 391–405.
Dennis, B., Patil, G. P., Rossi, O., Stehman, S., & Taille, C. (1979). A bibliography of literature on ecological diversity and related methodology. In J. F. Grassle, G. P. Patil, W. Smith, & C. Taillie (Eds.), Ecological diversity in theory and practice, vol 1, CPH (pp. 319–354). Fairland, MD: International Co-operative Publ. House.
Dorfman, R. (1979). A formula for the Gini coefficient. Review of Economics and Statistics, 61(February), 146–149.
Dragomir, S. S. (2010). Weighted f-Gini mean difference for convex and symmetric functions in linear spaces. Computers and Mathematics with Applications, 60, 734–743.
Druckman, A., & Jackson, T. (2008). Measuring resource inequalities: The concepts and methodology for an area-based Gini coefficient. Ecological Economics, 65, 242–252.
Fei, J. C. H., Ranis, G., & Kou, S. W. Y. (1978). Growth and the family distribution of income by factor components. Quarterly Journal of Economics, 92(1 (February)), 17–53.
Gastwirth, J. L. (1971). A general definition of the Lorenz curve. Econometrica, 1971, 1037–1039.
Gastwirth, J. L. (1972). The estimation of the Lorenz curve and Gini index. Review of Economics and Statistics, 54, 306–316.
Gibbs, J. P., & Martin, W. A. (1962). Urbanization, technology and the division of Labor: International patterns. American Sociological Review, 27(October), 667–677.
Gini, C. (1914). Reprinted: On the measurement of concentration and variability of characters (2005). Metron, LXIII(1), 3–38.
Gini, C. (1921). Measurement of inequality of incomes. Economic Journal, 30(121 (March)), 124–126.
Gini, C. (1936). Sur le coefficient de correlation comme caracteristique du degree de la concordance. Review of the International Statistical Institute, 4(3), 355–366 (French).
Gini, C. (1965). On the characteristics of Italian statistics. Journal of the Royal Statistical Society A (General), 128(1), 89–109.
Gini, C. (1966). Statistical methods. Roma: Instituto Di Statistica E Ricerca Sociale “Corrado Gini”, Universita Degli Studi di Roma.
Giorgi, G. M. (1990). Bibliographic portrait of the Gini concentration ratio. Metron, 48, 183–221.
Giorgi, G. M. (1993). A Fresh Look at the Topical Interest of the Gini Concentration Ratio. Metron, LI(1–2), 83–98.
Hart, P. E. (1975). Moment distributions in economics: An exposition. Journal of the Royal Statistical Society, A, 138(Part 3), 423–434.
Harter, H. L. (1978). A chronological annotated bibliography of order statistics, vol, 1: Pre-1950. Washington, DC: U.S. Government Printing Office.
Hettmansperger, T. P. (1984). Statistical inference based on ranks. New York: John Wiley and Sons.
Jaeckel, L. A. (1972). Estimating regression coefficients by minimizing the dispersion of the residuals. Annals of Mathematical Statistics, 43, 1449–1458.
Jenkins, S. P. (1988). Calculating income distribution indices from micro data. National Tax Journal, 41, 139–142.
Jorgenson, D. W., & Slesnick, D. T. (1984). Aggregate consumer behaviour and the measurement of inequality. The Review of Economic Studies, 51(3 (July)), 369–392.
Jurečková, J. (1969). Asymptotic linearity of a rank statistic in regression parameter. Annals of Mathematical Statistics, 40, 1889–1900.
Kolm, S. C. (1976). Unequal inequalities. Journal of Economic Theory, 16, 416–442.
Kőszegi, B., & Rabin, M. (2007). Reference-dependent risk attitude. American Economic Review, 97(4 (September)), 1047–1073.
Lambert, P. J., & Aronson, J. R. (1993). Inequality decomposition analysis and the Gini coefficient revisited. Economic Journal, 103, 1221–1227.
Lambert, P. J., & Decoster, A. (2005). The Gini coefficient reveals more. Metron, LXIII(3), 373–400.
Lambert, P. J. (2011). Lidia Ceriani and Paolo Verme’s paper “The origins of the Gini index: Extracts from Variabilità eMutabilità (1912) by Corrado Gini”. Journal of Economic Inequality. Forthcoming.
Lerman, R. I., & Yitzhaki, S. (1984). A note on the calculation and interpretation of the Gini index. Economics Letters, 15, 363–368.
Lerman, R. I., & Yitzhaki, S. (1989). Improving the accuracy of estimates of Gini coefficients. Journal of Econometrics, 42(1), 43–47.
Lieberson, S. (1969). Measuring population diversity. American Sociological Review, 34(December), 850–862.
McKenzie, G. W., & Pearce, I. F. (1982). Welfare measurement—A synthesis. American Economic Review, 72(4 (September)), 669–682.
Milanovic, B. (1997). A simple way to calculate the Gini coefficient, and some implications. Economics Letters, 56(1), 45–49.
Niewiadomska-Bugaj, M., & Kowalczyk, T. (2005). On grade transformation and its implications for copulas. Brazilian Journal of Probability and Statistics, 19, 125–137.
Olkin, I., & Yitzhaki, S. (1992). Gini regression analysis. International Statistical Review, 60(2), 185–196.
Portnov, B. A., & Felsenstein, D. (2010). On the stability of income inequality measures for regional analysis: Some evidence from simulation analysis and bootstrap tests. Socio-Economic Planning Sciences, 44, 212–219.
Puyenbroeck, T. V. (2008). Proportional representation, Gini coefficients, and the principle of transfers. Journal of Theoretical Polotics, 20(4), 498–526.
Pyatt, G. (1976). On the interpretation and disaggregation of Gini coefficient. The Economic Journal, 86(342), 243–255.
Pyatt, G., Chen, C., & Fei, J. (1980). The distribution of income by factor components. Quarterly Journal of Economics, 95(3), 451–473.
Ramasubban, T. A. (1958). The mean differences and the mean deviations of some discontinuous distributions. Biometrika, 45, 549–556.
Ramasubban, T. A. (1959). The generalized mean differences of the binomial and Poisson distributions. Biometrica, 46, 223–229.
Ramasubban, T. A. (1960). Some distributions arising in the study of generalized mean differences. Biometrika, 47, 469–473.
Rao, R. C. (1982). Diversity: Its measurement, decomposition, apportionment and analysis, Sankhya, Series A, 44(Pt. 1), 1–22.
Sen, A. K. (1973). On economic inequality. Oxford: Clarendon Press.
Serfling, R. J. (1980). Approximation theorems of mathematical statistics. New York: John Wiley and Sons.
Shorrocks, A. F. (1983). Ranking income distributions. Economica, 50, 3–17.
Silber, J. (1989). Factor components, population groups, and the computation of the Gini index of inequality. Review of Economics and Statistics, 71(2), 107–115.
Simpson, E. H. (1949). Measurement of diversity. Nature, 163, 688.
Stuart, A. (1954). The Correlation between variate-values and ranks in samples from a continuous distributions. British Journal of Statistical Psychology, 7, 37–44.
Von Mises, R. (1931). Wahrscheinlichkeitsrechnung, Leipzig-Wien.
Wold, H. (1935). A study of the mean difference, concentration curves and concentration ratios. Metron, 12(2), 39–58.
Yaari, M. E. (1988). A controversial proposal concerning inequality measurement. Journal of Economic Theory, 44(2), 381–397.
Yitzhaki, S. (1982a). Stochastic dominance, mean variance, and the Gini’s mean difference. American Economic Review, 72, 178–185.
Yitzhaki, S. (1983). On an extension of the Gini inequality index. International Economic Review, 24(3 (October)), 617–628.
Yitzhaki, S. (1996). On using linear regression in welfare economics. Journal of Business & Economic Statistics, 14(4 (October)), 478–486.
Yitzhaki, S. (1998). More than a dozen alternative ways of spelling Gini. Research on Economic Inequality, 8, 13–30.
Yitzhaki, S. (2003). Gini’s mean difference: A superior measure of variability for non-normal distributions. Metron, LXI(2), 285–316.
Yntema, D. B. (1933). Measures of the inequality in the personal distribution of wealth or income. Journal of the American Statistical Association, 28(184 (December)), 423–433.
Zenga, M. (1987). Concentration measures, section 4 in Ch. 2. In A. Naddeo (Ed.), Italian contributions to the methodology of statistics (pp. 42–82). Padua: Societa Italiana Di Statistica.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
Yitzhaki, S., Schechtman, E. (2013). More Than a Dozen Alternative Ways of Spelling Gini. In: The Gini Methodology. Springer Series in Statistics, vol 272. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-4720-7_2
Download citation
DOI: https://doi.org/10.1007/978-1-4614-4720-7_2
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-4719-1
Online ISBN: 978-1-4614-4720-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)