Sensitivity analysis for decision making

Sensitivity analysis is an essential step in the utilization of models by managers and decision-makers. Only through a rigorous application of sensitivity analysis, it is possible to fully exploit the informational content of a decision-support model, while understanding its limitations and the uncertainties involved. Several sensitivity analysismethods are available to help decision-analyst in solving different problems. They are illustrated in this article, starting from local methods, such as tornado diagrams, and continuing with reliability importance measures, all the way through nonparametric, screening, variance-based, distribution-based, and value-of-information-based methods.