Ricerc@Sapienza

We propose a novel Bayesian analysis of the p-variate skew-t model, providing a new parameterization, a set of non-informative priors and a sampler specifically designed to explore the posterior density of the model parameters. Extensions, such as the multivariate regression model with skewed errors and the stochastic frontiers model, are easily accommodated. A novelty introduced in the paper is given by the extension of the bivariate skew-normal model given in Liseo and Parisi (2013) to a more realistic p-variate skew-t model.

In this paper, we propose that relations between high-order
moments of data distributions, for example, between the skewness
(S) and kurtosis (K), allow to point to theoretical models with understandable
structural parameters. The illustrative data concern two
cases: (i) the distribution of income taxes and (ii) that of inhabitants,
after aggregation over each city in each province of Italy in 2011.
Moreover, from the rank-size relationship, for either S or K, in both
cases, it is shown that one obtains the parameters of the underlying