Milton, M J T (2002) Bayesian method for combining the results of repeated measurements with application to key comparison reference values. In: Joint BIPM - NPL Workshop on the impact of information technology in metrology, 16-19 September 2002, NPL, UK.

Full text not available from this repository.

Abstract

Various methods have been proposed for the calculation of a Reference Values for a Key Comparison that depend on the availability of a valid estimate for the uncertainty of the results from each laboratory. In general, these methods cannot incorporate data which has an uncertainty that is believed to be unreliable, or has been calculated on a different basis. Bayes Theorem can be used to overcome this limitation by providing a general method for combining a series of independent measurements of the same quantity. Examples of the application of a Bayesian method to this type of calculation have been developed. The method can also be applied in cases where specific “prior” information is available about the result of a Key Comparison.

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Subjects:	Analytical Science
Last Modified:	02 Feb 2018 13:17
URI:	https://eprintspublications.npl.co.uk/id/eprint/2669