Limits of detection in linear regression with errors in the concentration
✍ Scribed by F. Javier del Río Bocio; Jordi Riu; Ricard Boqué; F. Xavier Rius
- Publisher
- John Wiley and Sons
- Year
- 2003
- Tongue
- English
- Weight
- 158 KB
- Volume
- 17
- Category
- Article
- ISSN
- 0886-9383
- DOI
- 10.1002/cem.818
No coin nor oath required. For personal study only.
✦ Synopsis
Abstract
This paper discusses a method for calculating the limit of detection in analytical methods in which the calibration stage takes into account the errors in both concentrations and instrumental responses. The proposed method considers the heteroscedastic individual errors on both axes, i.e. it uses the bivariate least squares (BLS) regression method. The expressions were applied to X‐ray fluorescence (XRF) and capillary electrophoresis (CE) determinations to calculate the limits of detection of nine elements in solid rocks and three anions in water respectively. The limits of detection with these expressions have been compared with those obtained with ordinary least squares (OLS) and weighted least squares (WLS). The results show that the limits of detection when the BLS procedure is used are smaller than when the other techniques are used. Copyright © 2003 John Wiley & Sons, Ltd.
📜 SIMILAR VOLUMES
Some prooednws, based on studentized residuals and the diagonal elements of the 'hat' matrix, for the detection of unusual points in regreeeion are discussed. Them procedurea are quite simple but effective to uncover unusual structure of the date. Some examplee are given.
It is shown experimentally that, in stimulated Raman spectroscopy, electrostriction induced by the pump laser gives rise to a non-resonant signal detected on the probe laser. This phenomenon limits the detectivity of the experiment. A qualitative interpretation is given.