When working with positive mathematical programming (PMP) models it is generally admitted that it is not possible to consider in the modeled unit activities that are not present in the baseline situation of the unit. This constitutes a considerable drawback for traditional PMP techniques which cannot be applied in specific cases, in particular to the study of the impact of new agri-environmental programs that subsidize crops grown with technologies different to those applied in the baseline situation. This paper presents a method for dealing with these cases, which can be easily implemented as an extension of the traditional calibration techniques of PMP. The method is applied to a specific problem, using modified calibration expressions derived from the necessary Khun-Tucker conditions, assuming increasing marginal costs. The analysis of the results and their comparison with those obtained using a linear programming model permits a first evaluation of this methodological proposal.