Nonlinear inputs and diminishing marginal value in DEA

The conventional model structures presented in the data envelopment analysis (DEA) literature view all variables as behaving in a linear fashion, meaning that regardless of the amounts, large or small, of a variable held by the set of decision-making units, we apply the same multiplier to those various amounts. In certain situations this linearity assumption is not appropriate, and the conventional models need to be altered to accommodate nonlinear representations. In the current paper, we propose a modified DEA structure that captures certain forms of nonlinear behaviour within the additive DEA model, namely those that exhibit diminishing marginal value.