Оценивание расширенной неопределённости измерений при реализации байесовского подхода

Abstract

The problems of the expanded uncertainty evaluation in the first Committee Draft of the revised Guide to the Expression of Uncertainty in Measurement (GUM) based on the Bayesian approach are considered. In the article compares the well-known and proposed approaches to the expanded uncertainty evaluation based on the: current version of GUM, GOST R 8.736-2011 and the law of expanded uncertainty propagation. It is shown that a proposed method makes it possible to achieve good agreement between the estimates of the expanded uncertainty and the estimates obtained by the Monte Carlo method.