July 23, 1998
Statistical Engineering Division
Two-Component Model Measurement Error Model in Analytical Chemistry

Professor David M. Rocke
Center for Image Processing and Integrated Computing
The University of California, Davis

Often the standard deviation of analytical errors is assumed to increase proportionally to the concentration of the analyte, a model that cannot be used for very low concentrations. For near-zero amounts, the standard deviation is often assumed constant, which does not apply to larger quantities. Neither model applies across the full range of concentrations of an analyte. By positing two error components, one additive and one multiplicative, we obtain a model that exhibits sensible behavior at both low and high concentration levels. In this presentation, new data will be presented on the use of maximum likelihood and weighted least squares to estimate this model and comparisons will be made of this model to the more conventional model in which the standard deviation is a linear function of the mean concentration. Example data are drawn from measurements of organics and metals in water.

Date created: 6/5/2001
Last updated: 6/21/2001
Please email comments on this WWW page to sedwww@nist.gov.