Answers are grounded in this paper and cite their sources.
The shortcomings of the Guide to the Expression of Uncertainty in Measurement (GUM), which led to the need for its revision, are considered. The reasons for the limitation of using the Monte Carlo method for calculating measurement uncertainty in accredited test and calibration laboratories are listed. The claims to the first edition of the revised GUM, prepared by JCGM, are substantiated.The authors’ proposed ways to implement the algorithm for processing results and estimating measurement uncertainties based on the Bayesian approach are analyzed. The limitations on measurement modeling using the proposed GUM are considered. An algorithm for evaluation the input quantities, their standard uncertainties and covariances based on the available information is given. The nomograms to determine the parameters of the distribution laws of the measurand based on information obtained from the calibration certificate are built. The criteria for correction the numerical value of the measurand and its standard uncertainty with a non-linear model equation and significant uncertainties of the input quantities are substantiated.The expressions to obtain unbiased estimates of the measurand, as well as its standard uncertainties, are given. It is shown that to obtain the standard uncertainty of the measurand, it is necessary to take into account the kurtosis of the distribution of input quantities.An algorithm for evaluating the expanded uncertainty of the measurand allowing to take into account the laws of the distribution of input quantities is presented.
No takes yet. Share an insight, caveat, or question.
Неєжмаков et al. (2019) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: