ROBUST ORTHOGONAL REGRESSION FOR THE OUTLIER DETECTION WHEN COMPARING2 SERIES OF MEASUREMENT RESULTS

Citation
C. Hartmann et al., ROBUST ORTHOGONAL REGRESSION FOR THE OUTLIER DETECTION WHEN COMPARING2 SERIES OF MEASUREMENT RESULTS, Analytica chimica acta, 344(1-2), 1997, pp. 17-28
Citations number
22
Categorie Soggetti
Chemistry Analytical
Journal title
ISSN journal
00032670
Volume
344
Issue
1-2
Year of publication
1997
Pages
17 - 28
Database
ISI
SICI code
0003-2670(1997)344:1-2<17:RORFTO>2.0.ZU;2-G
Abstract
The application of a robust orthogonal regression procedure is describ ed for the outlier detection during the evaluation of a method compari son study and, in general, when comparing two series of measurement re sults. The procedure is based on the least median of the squared ortho gonal residuals (orthogonal LMS). It is concluded that the orthogonal LMS procedure is a useful screening tool to detect outlying values in a data set. Especially for data sets with extreme Values it is recomme nded to combine the robust data evaluation with a visual display. For the comparison of heteroscedastic methods, the program can easily be a dapted to a weighted orthogonal LMS variant.