In this work we approach the problem of model comparison between skew families. For the univariate skew model, we measure the sensitivity of the skewness parameter using the L1-distance between symmetric and asymmetric models and we obtain explicit expressions for some of these models. The main result is that the L1-distance between a representable elliptical distribution and a representable sk...

In portfolio theory, it is well-known that the distributions of stock returns often have non-Gaussian characteristics. Therefore, we need non-symmetric distributions for modeling and accurate analysis of actuarial data. For this purpose and optimal portfolio selection, we use the Tail Mean-Variance (TMV) model, which focuses on the rare risks but high losses and usually happens in the tail of r...

In this paper, we compute doubly truncated moments for the selection elliptical class of distributions, including some multivariate asymmetric versions well-known such as normal, Student’s t, slash, among others. We address members family, establishing neat formulation high-order and its first two moments. establish sufficient necessary conditions existence these Further, propose optimized meth...

A Bayesian Prediction using the Elliptical Processes (EP) and the Skew Gaussian Processes (SGP) is proposed, motivated by a Bayesian model for heavy, light tailed or skewed real data. We define weak third order stationary for the Skew Gaussian Processes. Sometimes the family of distributions have dimensional coherency (consistency) property which is important for prediction. We use a Markov Cha...

Normality of random effects and error terms is a routine assumption for linear effects mixed models. However, such assumption may be unrealistic, obscuring important features of withinand among-unit variation. A simple and robust Bayesian parametric approach that relaxes this assumption by using a multivariate Skew elliptical distributions, which includes the Skew-t, Skew-normal, t-Student, and...

In recent years, the skew-normal models introduced by Azzalini (1985)—and their multivariate generalizations from Azzalini and Dalla Valle (1996)—have enjoyed an amazing success, although an important literature has reported that they exhibit, in the vicinity of symmetry, singular Fisher information matrices and stationary points in the profile log-likelihood function for skewness, with the usu...

This article proposes a unified class of generalized location-scale mixture multivariate elliptical distributions and studies integral stochastic orderings random vectors following such distributions. Given vector Z, independent X Y, the scale parameter this is mixed with function α(Z) its skew another β(Z). Sufficient (and necessary) conditions are established for stochastically comparing diff...

Bartolucci et al.(2003) extended the distribution assumption from the normal (Lyles et al., 2000) to the elliptical contoured distribution (ECD) for random regression models used in analysis of longitudinal data accounting for both undetectable values and informative drop-outs. In this paper, the random regression models are constructed on the multivariate skew ECD. A real data set is used to i...