Total Sensitivity Gradients and Uncertainty Budgets for Nonlinear Measurement Functions with Independent Inputs
Mark B. Campanelli, Raghu N. Kacker, RUEDIGER KESSEL
A novel variance-based measure for global sensitivity analysis, termed a total sensitivity gradient~(TSG), is presented for constructing uncertainty budgets under the Guide to the Expression of Uncertainty~(GUM) framework for nonlinear measurement functions with independent inputs. TSGs are motivated by the metrologist's desire to rank measurement function inputs in terms of which inputs' additional precision would most effectively improve the measurand's precision. TSGs can be particularly useful where application of the first supplement to the GUM is indicated because of the inadequacy of measurement function linearization. However, TSGs reduce to a commonly understood variance decomposition in the case of a linear(ized) measurement function with independent inputs for which the original GUM readily applies. The usefulness of TSGs is illustrated by an example from the first supplement to the GUM, and comparison to other available sensitivity measures is made.
, Kacker, R.
and Kessel, R.
Total Sensitivity Gradients and Uncertainty Budgets for Nonlinear Measurement Functions with Independent Inputs, Measurement Science and Technology, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=910150
(Accessed December 9, 2023)