Gini’s Mean difference: a superior measure of variability for non-normal distributions

Summary -O fall measures of variability, the variance is by far the most popular. This paper argues that Gini’s Mean Difference (GMD), an alternative index of variability, shares many properties with the variance, but can be more informative about the properties of distributions that depart from normality. Its superiority over the variance is important whenever one is interested in one or more of the following properties: (a) stochastic dominance: the GMD can be used to form necessary conditions for stochastic dominance, while the variance cannot; (b) exchangeability: the GMD has two correlation coefficients associated with it, the difference between them being sensitive to the exchangeability between the marginal distributions. This property may play an important role whenever the ”index number” problem is severe, (i.e., whenever the choice of the base for comparison between two marginal distributions may determine the direction of the results), or whenever the investigation procedure is based on an optimization procedure; (c) stratification: when the overall distribution is composed of sub-populations, the GMD is sensitive to stratification among subpopulations. The paper surveys the properties of the two indices of variability and discusses their relevance to several fields of research.

[1]  S. Yitzhaki,et al.  The Mean-Gini Efficient Portfolio Frontier , 2005 .

[2]  Sebastian Galiani,et al.  Introduction to Symposium: the labor market in Latin America , 2004 .

[3]  Edna Schechtman,et al.  A Family of Correlation Coefficients Based on the Extended Gini Index , 2003 .

[4]  Michel Terraza,et al.  Decomposition of Gini and the generalized entropy inequality measures , 2003 .

[5]  S. Yitzhaki,et al.  A Family of Correlation Coefficients Based on Extended Gini , 2002 .

[6]  S. Yitzhaki,et al.  Derivation of the Mean-Gini Efficient Portfolio Frontier , 2002 .

[7]  M. Rockinger,et al.  Conditional Dependency of Financial Series , 2002 .

[8]  Eric Jondeau,et al.  Conditional Dependency of Financial Series: An Application of Copulas , 2001 .

[9]  Branko Milanovic,et al.  Decomposing World Income Distribution: Does the World Have a Middle Class? , 2001 .

[10]  Efe A. Ok,et al.  Lorenz Dominance and the Variance of Logarithms , 1999 .

[11]  S. Yitzhaki,et al.  On the proper bounds of the Gini correlation , 1999 .

[12]  J. Formby,et al.  The coefficient of variation, stochastic dominance and inequality: A new interpretation , 1999 .

[13]  S. Yitzhaki Necessary and Sufficient Conditions for Dominance Using Generalized Lorenz Curves , 1999 .

[14]  R. Nelsen An Introduction to Copulas , 1998 .

[15]  S. Yitzhaki On Using Linear Regressions in Welfare Economics , 1996 .

[16]  R. Davidson,et al.  Statistical Inference for the Measurement of the Incidence of Taxes and Transfers , 1997 .

[17]  K. V. Chow,et al.  Testing for Marginal Changes in Income Distributions with Lorenz and Concentration Curves , 1994 .

[18]  A. W. Kemp,et al.  Kendall's Advanced Theory of Statistics. , 1994 .

[19]  Shlomo Yitzhaki,et al.  Economic distance and overlapping of distributions , 1994 .

[20]  R. Eubank,et al.  A test for second order stochastic dominance , 1993 .

[21]  Ingram Olkin,et al.  Gini Regression Analysis , 1992 .

[22]  H. Levy Stochastic dominance and expected utility: survey and analysis , 1992 .

[23]  Paul D. Thistle,et al.  Convergence of the South and non-South income distributions 1969-1979. , 1992 .

[24]  Wei-Min Huang,et al.  Evaluating correlation with proper bounds , 1992 .

[25]  Robert I. Lerman,et al.  INCOME STRATIFICATION AND INCOME INEQUALITY , 1991 .

[26]  I. Olkin,et al.  Concentration indices and concentration curves , 1991 .

[27]  S. Kotz,et al.  A New Approach to Dependence in Multivariate Distributions , 1991 .

[28]  S. Yitzhaki On the Sensitivity of a Regression Coefficient to Monotonic Transformations , 1990, Econometric Theory.

[29]  J. Silber Factor Components, Population Subgroups and the Computation of the Gini Index of Inequality , 1989 .

[30]  M. Yaari,et al.  A controversial proposal concerning inequality measurement , 1988 .

[31]  S. Yitzhaki,et al.  Welfare Dominance: an Application to Commodity Taxation , 1987 .

[32]  C. Dagum,et al.  Measuring the Economic Affluence Between Populations of Income Receivers , 1987 .

[33]  Edna Schechtman,et al.  A Measure of Association Based on Gini's Mean Difference , 1987 .

[34]  G. Giorgi,et al.  About a general method for the lower and upper distribution-free bound on Gini's concentration ratio from grouped data , 1987 .

[35]  Shlomo Yitzhaki,et al.  Mean-Gini, Portfolio Theory, and the Pricing of Risky Assets , 1984 .

[36]  D. Jorgenson,et al.  Aggregate Consumer Behaviour and the Measurement of Inequality , 1984 .

[37]  Shlomo Yitzhaki,et al.  On an Extension of the Gini Inequality Index , 1983 .

[38]  Russell Davidson,et al.  Distribution-Free Statistical Inference with Lorenz Curves and Income Shares , 1983 .

[39]  A. Shorrocks The Impact of Income Components on the Distribution of Family Incomes , 1983 .

[40]  Arne Sandström,et al.  Measuring Income Inequality , 1983 .

[41]  H. Harter,et al.  The chronological annotated bibliography of order statistics , 1983 .

[42]  S. Yitzhaki Stochastic Dominance, Mean Variance, and Gini's Mean Difference , 1982 .

[43]  Welfare Measurement-A Synthesis , 1982 .

[44]  R. Serfling Approximation Theorems of Mathematical Statistics , 1980 .

[45]  N. Kakwani,et al.  Income inequality and poverty , 1980 .

[46]  A. Deaton,et al.  The Distance Function in Consumer Behaviour with Applications to Index Numbers and Optimal Taxation , 1979 .

[47]  H. Levy,et al.  Approximating Expected Utility by a Function of Mean and Variance , 1979 .

[48]  R. Koenker,et al.  Asymptotic Theory of Least Absolute Error Regression , 1978 .

[49]  C. Goldie Convergence theorems for empirical Lorenz curves and their inverses , 1977, Advances in Applied Probability.

[50]  N. Kakwani Applications of Lorenz Curves in Economic Analysis , 1977 .

[51]  D. Suits Measurement of Tax Progressivity , 1977 .

[52]  Graham Pyatt,et al.  On the interpretation and disaggregation of GINI coefficients , 1976 .

[53]  V. Barnett,et al.  Concomitants and correlation estimates , 1976 .

[54]  P. E. Hart Moment Distributions in Economics: An Exposition , 1975 .

[55]  D. M. Grether Correlations with ordinal data , 1974 .

[56]  J. Gastwirth The Estimation of the Lorenz Curve and Gini Index , 1972 .

[57]  Joseph L. Gastwirth,et al.  A General Definition of the Lorenz Curve , 1971 .

[58]  M. Rothschild,et al.  Increasing risk: I. A definition , 1970 .

[59]  H. Levy,et al.  Efficiency analysis of choices involving risk , 1969 .

[60]  V. M. Rao Two Decompositions of Concentration Ratio , 1969 .

[61]  M. Feldstein,et al.  Mean-Variance Analysis in the Theory of Liquidity Preference and Portfolio Selection , 1969 .

[62]  Josef Hadar,et al.  Rules for Ordering Uncertain Prospects , 1969 .

[63]  H. A. David Miscellanea: Gini's mean difference rediscovered , 1968 .

[64]  H. A. David Gini's Mean Difference Rediscovered , 1968 .

[65]  W. Runciman Relative Deprivation and Social Justice , 1966 .

[66]  C. Gini On the Characteristics of Italian Statistics , 1965 .

[67]  Thomas E. Lasswell,et al.  Class and stratum , 1965 .

[68]  Some distributions arising in the study of generalized mean differences , 1960 .

[69]  T. A. Ramasubban The generalized mean differences of the binomial and Poisson distributions , 1959 .

[70]  T. A. Ramasubban The mean difference and the mean deviation of some discontinuous distributions , 1958 .

[71]  D. Darling The Kolmogorov-Smirnov, Cramer-von Mises Tests , 1957 .

[72]  Alan Stuart,et al.  THE CORRELATION BETWEEN VARIATE-VALUES AND RANKS IN SAMPLES FROM A CONTINUOUS DISTRIBUTION , 1954 .

[73]  E. H. Simpson Measurement of Diversity , 1949, Nature.

[74]  Maurice G. Kendall,et al.  Rank Correlation Methods , 1949 .

[75]  W. Hoeffding A Class of Statistics with Asymptotically Normal Distribution , 1948 .

[76]  H. Cramér On the composition of elementary errors: Second paper: Statistical applications , 1928 .