An Alternative View of Sensitivity in the Analysis of Computer Codes

This paper addresses the analysis of uncertainty in the output of computer models arising from uncertainty in inputs (parameters). Uncertainty of this type, which is separate and distinct from the randomness of a stochastic model, most often arises when proper input values are imprecisely known. Uncertainty in the output is quantified in its probability distribution, which results from treating the inputs as random variables. The assessment of which inputs are important with respect to uncertainty is done relative to the probability distribution of the output.