The NDS What-If Analysis Tool is designed to perform a brainstorming technique with the goal to determine how the performance projections are influenced by the variations of the hypotheses on which these projections are based. It provides therefore a structured method for determining which predictions relating to formulations changes can go wrong, judging the feasibility and the consequences of the simulations carried out before they occur.
The process of recalculating outcomes under alternative assumptions to determine the impact of a variable under What-If analysis can be useful for a range of purposes including:
− Testing the robustness of the results of the formulation process in the presence of uncertainty.
− Increased understanding of the relationships between input and output variables for diet formulation and model evaluation.
− Uncertainty reduction, through the identification of model inputs that cause significant uncertainty in the output and should therefore be the focus of attention in order to increase the accuracy of the outcomes.
− Searching for errors in the formulation inputs by encountering unexpected relationships between inputs and outputs.
− Model interpretation and simplification through a better understanding of the model inputs that have no effect on the output.
− Enhancing communication among platform users, e.g. by making recommendations more credible, understandable, compelling or persuasive.
− Finding input factors for which the model output is either maximum or minimum or meets some optimum criterion (see also optimization process).
− During the calibrating stage of the model, given the large number of parameters, a preliminary What-If test can ease the calibration stage by focusing on the sensitive parameters. Not knowing the sensitivity of parameters can result in time being uselessly spent on non-sensitive ones.
− To seek to identify important connections between observations, model inputs, and predictions, leading to the development of better diets formulation.