Investigation on the relationship between analytical precision and concentration with iteratively reweighted least-squares linear regression method

It is very important to investigate the relationship between analytical pre cision and concentration for quality control and assessment of analytical r esults. A set of analytical data of trace elements in soil and water deposi ts (Chinese certified reference materials) was studied for the relationship between the analytical precision of collaboration trials (i.e. reproducibi lity) and the concentration of the analytes. Iteratively reweighted least-s quares (IRLS) linear regression, a robust method, was employed in this stud y. The linear relationship between the standard deviation and concentration was successfully established. On comparison with the conventional least-sq uares (LS) method, the results of IRLS linear regression are superior to th ose of LS. (C) 1999 Elsevier Science B.V. All rights reserved.