In this paper we discussed inference aspects of the skew-normal calibration comparative models (SN-CCM) following both; a classical and Bayesian approach, extending the usual normal calibration comparative models (N-CCM) in order to avoid data transformation. To the proposed model we consider the maximum likelihood approach to estimation via the EM-algorithm and derive the observed information matrix allowing direct inference implementation, then we conduct the Bayesian approach via Markov chain Monte Carlo procedure. The univariate skew-normal distribution that will be used in this work was introduced by Sahu et al (2003) which has a shape parameter that defines the direction of the asymmetric of the distribution, usually called the skew-ness parameter. Sahu’s skew-normal distribution is attractive because estimation of the skewness parameter does not present the same difficult as is the case with Azzalini’s (1985) one the procedures are illustrated with a numerical example.