Draft GUM Supplement 1 and Bayesian analysis

Abstract

The relation between uncertainty evaluation according to the recent draft of GUM Supplement 1 and the application of Bayesian statistics including Bayes' theorem is considered. In the case of a Type A evaluation of uncertainty, repeated measurement indications are regarded as independently drawn from normal frequency distributions and, according to its suggestion, the numerical evaluation method of Supplement 1 is applied after having assigned scaled and shifted t-distributions to the corresponding input quantities. It will be shown that this approach is equivalent to a Bayesian analysis using Bayes' theorem with commonly used prior distributions.