Sensitivity analysis and related analysis : A survey of statistical techniques

This paper reviews the state of the art in five related types of analysis, namely (i) sensitivity or what-if analysis, (ii) uncertainty or risk analysis, (iii) screening, (iv) validation, and (v) optimization. The main question is: when should which type of analysis be applied; which statistical techniques may then be used? This paper distinguishes the following five stages in the analysis of a simulation model. 1) Validation: the availability of data on the real system determines which type of statistical technique to use for validation. 2) Screening: in the simulation's pilot phase the really important inputs can be identified through a novel technique, called sequential bifurcation, which uses aggregation and sequential experimentation. 3) Sensitivity analysis: the really important inputs should be This approach with its five stages implies that sensitivity analysis should precede uncertainty analysis. This paper briefly discusses several case studies for each phase.