A generalization of the beta distribution with applications

This paper introduces a five-parameter beta distribution (GB) which nests the generalized beta and gamma distributions and includes more than thirty distributions as limiting or special cases. The generalized beta leads to an exponential generalized beta (EGB) distribution which includes generalized forms of the logistics, exponential, Gompertz and Gumbell distributions, and the normal as special cases. The EGB family of distributiosn provides the basis for partially adaptive estimation of econometric models with possibly skewed and leptokurtic error distributions. Applications of the models to investigating the distribution of income, stock returns and in regression analysis are considered.