An analysis of the extended mean Gini coefficient as an alternative measure of risk in investment decision making under uncertainty

Abstract

The methods traditionally used for comparing uncertain prospects in investment decision making under uncertainty are the mean variance and the stochastic dominance approaches. Yitzhaki (1982) has recently presented an alternative model based upon the extended mean Gini coefficient (EMG) to compare uncertain prospects. The EMG model possesses the attractive features of each of the mean variance and stochastic dominance models without their apparent disadvantages. The EMG model has simplicity of a two parameter model and EMG efficiency implies second order stochastic dominance. Theoretically the EMG model is consistent with the behaviour of investors under conditions of uncertainty for a wider class of probability distributions, and thus appears to be more adequate than variance as a measure of risk. This study empirically compares the EMG model with that of the mean variance model with respect to, the generation of efficient frontiers, capital asset pricing, portfolio performance and farm planning under uncertainty. The major finding of the study is that the extended mean Gini coefficient is a viable alternative to variance as a measure of risk. Show more