|
Products Software UncertaintyAnalyzer 3.0 Software Comparison Combining Uncertainties
Combining Uncertainties |
When combining uncertainties we must account for any correlations between measurement process errors and, for multivariate analyses, any cross-correlations between component errors. For multivariate analyses, it is also important that the uncertainties are multiplied by the appropriate sensitivity coefficients. Finally, we must also estimate the effective degrees of freedom associated with the combined uncertainty.
A ü in the cell indicates that the particular capability or feature is available. Alternatively, a blank cell indicates that the capability or feature is not available. Comments and footnotes are included to clarify significant differences between software applications or to provide necessary details.
1 In a multivariate analysis, the sensitivity coefficient of a variable is the partial derivative of the equation that defines a quantity of interest with respect to that variable. The product of the sensitivity coefficient and the variable's standard uncertainty reflects the contribution of the uncertianty in the variable's error tot he overall uncertainty in the computed quantity. 2 A Sensitivity Coefficient Worksheet can be used to compute partial derivatives for up to 10 variables. The computed sensitivity coefficients must then be copied and pasted into the appropriate cells on the Uncertainty Budget Worksheet. 3 Computed using Welch-Satterthwaite formula given in Annex G of the GUM. 4 Computed by multiplying the combined uncertainty by 1) user specified coverage factor or 2) coverage factor computed from effective degrees of freedom and user specified confidence level. |
Home | Company | Products | Services | Training | Updates | Freeware | Articles | Help | Links
Integrated Sciences Group
14608 Casitas Canyon Road • Bakersfield, CA 93306
Phone 1-661-872-1683 • FAX 1-661-872-3669
Privacy Policy Return Policy Shipping Info
Page Updated February 12, 2015