Deterministic versus stochastic sensitivity analysis in investment problems: An environmental case study

Sensitivity analysis in investment problems is an important tool to determine which factors can jeopardize the future of the investment. Information on the probability distribution of those factors that affect the investment is mostly lacking. In those situations the analysts have two options: (i) apply a method that does not require knowledge of that distribution, or (ii) make assumptions about the distribution. In both approaches sensitivity analysis should result in practical information about the actual importance of potential factors. For approach (i) we apply statistical design of experiments in combination with regression analysis or meta-modeling. For approach (ii) we investigate five types of relationships between the model output and each individual factor: Pearson's p, Spearman's rank correlation, and location, dispersion, and statistical dependence. We introduce two distribution types popular with practitioners: uniform and triangular. In an environmental case study both approaches identify the same factors as important.