The Indication of a moment independent measure and its new calculation method

Liu, Q.; Homma, Toshimitsu

In risk assessment problems, the variations of input parameters are transferred through the model to the output, and bring about the issue of output uncertainty. The study of how the uncertainty in the model output can be apportioned to the variations of input parameters is the job of sensitivity analysis. Borgonovo argued that an ideal measure should be global, model-free and moment-independent. He proposed a new uncertainty importance measure, which is called Delta. The calculation method of Delta is based on measuring the surrounded area between two PDFs (Probability Density Functions) of the model output. By analyzing this calculation method, the authors found that the area surrounded by two PDFs is equivalent to two times of the algebraic sum of the vertical deviations between their corresponding CDFs at the intersection points of these two PDFs. Therefore, the author proposed a new method to calculate Delta. An analysis shows that this measure will improve the calculation accuracy of Delta.