Bayesian inference on the scalar skew-normal distribution

In this paper we discuss a Bayesian analysis of the scalar skew-normal model. This model defines a class of distributions that extends the Gaussian model by including a shape parameter. Although the skew-normal model has nice proper ties, it presents some problems with the estimation of the shape parameter. To avoid these drawbacks, we explore through some examples the use of Severini’s integrated likelihood function in Bayesian inference