Statistical Engineering Division, ITL
The Statistical Engineering Division supports the Standard Reference Materials (SRMs) Program and the other NIST laboratories by collaborating directly with chemists and other scientists engaged in the certification of SRMs. All division staff are engaged in this activity.
Standard Reference Materials are artifacts or chemical compositions that are manufactured according to strict specifications and certified by NIST for one or more quantities of interest. SRMs represent one of the primary vehicles for disseminating measurement technology to industry.
The process of developing a new SRM can take up to five years or more and goes through several phases: 1) development and validation of a measurement method; 2) design of a prototype; 3) stability testing; 4) study of measurement error; 5) certification; and 6) uncertainty analysis. Statisticians advise on the design and analysis of experiments at all phases; develop methods for estimation for data taken by different analytical methods; reconcile interlaboratory differences; and combine all information to produce a certified value and statement of uncertainty.
In 1996, division staff collaborated on an unusually large number of SRMs, eighty or more, covering a variety of applications including: chemical (e.g., sulfur concentration in coke); health (e.g., glucose in human serum); dimensional (e.g., sinusoidal roughness); materials (e.g., diameters of polystrene spheres); environmental (e.g, lead in paint); scientific (e.g., magnification of scanning electron microscopes); and semiconductor manufacturing (e.g., resistivity of silicon wafers).
The large workload of SRMs has led the division to consider more efficient methods for handling the statistical design and analyses of SRMs. As a start, a standardized protocol for certifying gas cylinders is being developed in collaboration with chemists from CSTL. Typically, fifty or more issues of cylinders (with various gases and concentration levels) are certified per year. It is expected that once the analysis template has been coded into software, the chemists will handle the certifications with only occasional assistance from the statisticians.
If this experiment is successful, it will have three salutary effects. The time spent on SRMs within SED will decrease dramatically. The creation of software modules for other classes of SRMs with common analysis characteristics will proceed. And, NIST's long term goal of transferring measurement technology and certification capability for gas cylinders to laboratories outside of NIST will become feasible.
More information on statistical issues related to specific SRMs can be found in the body of this document.
Date created: 7/20/2001