A statistical procedure for the assessment of bias in analytical methods using conditional probabilities

Frenkel, R and Farrance, I 2017, 'A statistical procedure for the assessment of bias in analytical methods using conditional probabilities', Accreditation and Quality Assurance, vol. 22, no. 5, pp. 265-273.


Document type: Journal Article
Collection: Journal Articles

Title A statistical procedure for the assessment of bias in analytical methods using conditional probabilities
Author(s) Frenkel, R
Farrance, I
Year 2017
Journal name Accreditation and Quality Assurance
Volume number 22
Issue number 5
Start page 265
End page 273
Total pages 9
Publisher Springer
Abstract A new approach is described for the simultaneous treatment of bias and imprecision in clinical chemistry. The approach makes use of the general law of conditional probabilities. The result is a density distribution of the measurand that incorporates both imprecision and bias and avoids the contentious linear combination of these quantities as a 'total error'. This leads naturally to a figure-of-merit in proficiency testing or method comparison that has intuitive visual appeal. We also discuss an established figure-of-merit in proficiency testing, namely the E n number.
Subject Biological Mathematics
Applied Statistics
Clinical Chemistry (diagnostics)
Keyword(s) Analytical method uncertainty
Bias
Conditional probability
E number n
Overlap area
Proficiency testing
Sigma-metric
Total error
DOI - identifier 10.1007/s00769-017-1274-8
Copyright notice © Springer-Verlag 2017
ISSN 0949-1775
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 4 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 60 Abstract Views  -  Detailed Statistics
Created: Thu, 18 Jan 2018, 12:37:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us