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

By Shlomo Yitzhaki. 2003

225 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e4d00851cbbadf386ed051397cabff464a0d2585

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Energy statistics: A class of statistics based on distances (2013, methodology): “A familiar example is the U -statistic for dispersion, Gini’s mean difference [65], 1 n(n− 1) n ∑”
Understanding Instrumental Variables in Models with Essential Heterogeneity (2006, unknown): “Letting Ji = J (Zi), we can follow Yitzhaki (1996, 2004), as summarized in Appendix A, to write the two stage least squares estimator as a weighted average of ordered pairwise TSLS estimators ∆TSLS = X 1≤i≤N−1 ∙ Yi+1 − Yi E∗(D | J (Z) = ji+1)−E∗(D | J (Z) = ji) ¸ ω (i)1 [E∗ (D | J (Z) = ji+1) 6= E∗…”
Space and the Measurement of Income Segregation (2007, unknown): “As demonstrated by Yitzhaki (2003), Gini-based measures place smaller weights on differences among adjacent observations located farther from the median than do measures based on the variance.”
Probabilistic quantitative precipitation forecasting using Ensemble Model Output Statistics (2013, background): “It has certain properties, however, that make it an appealing dispersion measure for precipitation forecasts (see also Yitzhaki, 2003): • it is more robust than the standard deviation because it uses absolute rather than squared diﬀerences • unlike the interquartile range or the median absolute…”
ON CUMULATIVE RESIDUAL EXTROPY (2020, background): “It is argued by Yitzhaki [29] that the GMD, as a measure of variability, shares many properties of the variance of X and is more informative than the variance for the distributions that are far from normality.”