SED navigation bar go to SED home page go to SED publications page go to NIST home page SED Home Page SED Contacts SED Projects SED Products and Publications Search SED Pages

contents     previous     next

4.3 Workshop on Evaluation and Expression of Measurement Uncertainty for NIST WERB from February 1999 to November 1999

Raghu N. Kacker
Statistical Engineering Division, ITL

This workshop was made up of six seminars conducted over nine hours for the members of Washington Editorial Review Board (WERB) from February 1999 to November 1999. This workshop led to the discovery of trapezoidal distribution as a useful model for the distribution of the measurand based on results from two or more independent and equally trustworthy methods. The first seminar discussed the NIST Policy on expression of uncertainty as described by Technical Note 1297. The second seminar discussed general metrological and statistical terms and the need of a statement of uncertainty in measurements. The third seminar discussed the procedure for evaluating and reporting uncertainty as described in the ISO Guide to the Expression of Uncertainty in Measurement (commonly referred to as the GUM). The fourth seminar discussed a calibration example and discussed the statistical methods commonly used in NIST to evaluate the uncertainty of chemical batch reference materials as described by Schiller in Special Publication 260-125. The fifth seminar discussed the philosophical and methodological basis of the GUM. While preparing for this seminar I got convinced that the expanded uncertainties based on t-values are not consistent with the rest of the GUM. Also in most practical applications, sufficient information does not exist to associate a coverage probability with a stated expanded uncertainty interval (EUI). Fortunately in many applications a default EUI based of coverage factor or 2 or 3 is sufficient for the needs. The sixth seminar was on a method to quantify uncertainty due to bias in chemical analysis. I hope to consolidate this series of seminars into a workshop for NIST and external audience. During a visit to CENAM, the Mexican counterpart of NIST, I learned that there is a great need of coherent interpretation of the GUM so it could be used as a basis for more specialized guidance for specific applications.

contents     previous     next

Date created: 7/20/2001
Last updated: 7/20/2001
Please email comments on this WWW page to