A family of conjugated distributions for a given type of copulas is defined in this paper. Those copulas can be written as a mixture of d-dimensional parameter exponential functions. The generalized Farlie-Gumbel-Morgenstern copula is an example of this representation. This family is used to illustrate the estimation technique with real data. Also, the applicability of Bayesian predictive approach is shown in an education policy issue by defining goals for the number of students per class that leads to improve their performance at school. Ver menos