Measurement Techniques

, Volume 56, Issue 6, pp 584–590

Application of Bayesian model averaging using a fixed effects model with linear drift for the analysis of key comparison CCM.P-K12

  • O. Bodnar
  • A. Link
  • K. Klauenberg
  • K. Jousten
  • C. Elster
Article

DOI: 10.1007/s11018-013-0249-3

Cite this article as:
Bodnar, O., Link, A., Klauenberg, K. et al. Meas Tech (2013) 56: 584. doi:10.1007/s11018-013-0249-3

In this paper, we extend a recently proposed procedure for the analysis of key comparison data to the case where the traveling standard shows a linear drift. The procedure is based on a fixed effects model and assumes that a certain number of the laboratories measure without bias. The analysis is carried out by applying Bayesian model averaging to all possible different models, each assuming zero biases for a different subset of laboratories. The method is applied to the key comparison CCM.P-K12.

Keywords

fixed effects model Bayesian averaging method of (weighted) least squares bias 

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • O. Bodnar
    • 1
  • A. Link
    • 1
  • K. Klauenberg
    • 1
  • K. Jousten
    • 1
  • C. Elster
    • 1
  1. 1.Physikalisch-Technische Bundesanstalt (PTB)BerlinGermany