Correction of incoherence in statistical matching

We deal with the statistical matching problem, with particular emphasis on the managing of inconsistencies. In fact, when structural zeros among variables are present, incoherence on the probability evaluations can arise. The aim of this paper is to remove such incoherences by using different methods based on distances minimization or least commitment imprecise probabilities extensions. We compare these methods through an exemplifying practical example that carries out to the light peculiarities of the statistical matching problem.