Title: Constructing distributions via the beta-generating technique
Authors: Seitebaleng Makgai - University of Pretoria (South Africa) [presenting]
Andriette Bekker - University of Pretoria (South Africa)
Mohammad Arashi - Ferdowsi University of Mashhad (Iran)
Jaco Visagie - University of Pretoria, South Africa (South Africa)
Abstract: The beta-generating technique, is a well known mechanism for influencing the tails, the skewness, as well as the goodness of fit of a distribution. Two classes of multivariate beta distributions are proposed and constructed through this nesting technique, where various baseline distributions are considered. General properties such as the cumulative distribution function (cdf), probability density function (pdf), dependence structures and moments are investigated for the developed distributions. The maximum likelihood estimation is used here for parameter estimates, where the usefulness and performance of the distributions are illustrated under various datasets.