Comparison of the single channel and multichannel (multivariate) concepts of selectivity in analytical chemistry

Zsanett Dorkó, Tatjana Verbić, G. Horvai

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Abstract Different measures of selectivity are in use for single channel and multichannel linear analytical measurements, respectively. It is important to understand that these two measures express related but still distinctly different features of the respective measurements. These relationships are clarified by introducing new arguments. The most widely used selectivity measure of multichannel linear methods (which is based on the net analyte signal, NAS, concept) expresses the sensitivity to random errors of a determination where all bias from interferents is computationally eliminated using pure component spectra. The conventional selectivity measure of single channel linear measurements, on the other hand, helps to estimate the bias caused by an interferent in a biased measurement. In single channel methods expert knowledge about the samples is used to limit the possible range of interferent concentrations. The same kind of expert knowledge allows improved (lower mean squared error, MSE) analyte determinations also in "classical" multichannel measurements if those are intractable due to perfect collinearity or to high noise inflation. To achieve this goal bias variance tradeoff is employed, hence there remains some bias in the results and therefore the concept of single channel selectivity can be extended in a natural way to multichannel measurements. This extended definition and the resulting selectivity measure can also be applied to the so-called inverse multivariate methods like partial least squares regression (PLSR), principal component regression (PCR) and ridge regression (RR).

Original languageEnglish
Article number15403
Pages (from-to)40-49
Number of pages10
JournalTalanta
Volume139
DOIs
Publication statusPublished - Aug 1 2015

Fingerprint

Chemical analysis
Economic Inflation
Least-Squares Analysis
Noise
Random errors

Keywords

  • Bias variance tradeoff
  • Error inflation
  • Interference
  • Multivariate
  • Selectivity

ASJC Scopus subject areas

  • Chemistry(all)

Cite this

Comparison of the single channel and multichannel (multivariate) concepts of selectivity in analytical chemistry. / Dorkó, Zsanett; Verbić, Tatjana; Horvai, G.

In: Talanta, Vol. 139, 15403, 01.08.2015, p. 40-49.

Research output: Contribution to journalArticle

@article{d2971d17e7664667b8fbdc6d749b851e,
title = "Comparison of the single channel and multichannel (multivariate) concepts of selectivity in analytical chemistry",
abstract = "Abstract Different measures of selectivity are in use for single channel and multichannel linear analytical measurements, respectively. It is important to understand that these two measures express related but still distinctly different features of the respective measurements. These relationships are clarified by introducing new arguments. The most widely used selectivity measure of multichannel linear methods (which is based on the net analyte signal, NAS, concept) expresses the sensitivity to random errors of a determination where all bias from interferents is computationally eliminated using pure component spectra. The conventional selectivity measure of single channel linear measurements, on the other hand, helps to estimate the bias caused by an interferent in a biased measurement. In single channel methods expert knowledge about the samples is used to limit the possible range of interferent concentrations. The same kind of expert knowledge allows improved (lower mean squared error, MSE) analyte determinations also in {"}classical{"} multichannel measurements if those are intractable due to perfect collinearity or to high noise inflation. To achieve this goal bias variance tradeoff is employed, hence there remains some bias in the results and therefore the concept of single channel selectivity can be extended in a natural way to multichannel measurements. This extended definition and the resulting selectivity measure can also be applied to the so-called inverse multivariate methods like partial least squares regression (PLSR), principal component regression (PCR) and ridge regression (RR).",
keywords = "Bias variance tradeoff, Error inflation, Interference, Multivariate, Selectivity",
author = "Zsanett Dork{\'o} and Tatjana Verbić and G. Horvai",
year = "2015",
month = "8",
day = "1",
doi = "10.1016/j.talanta.2015.02.030",
language = "English",
volume = "139",
pages = "40--49",
journal = "Talanta",
issn = "0039-9140",
publisher = "Elsevier",

}

TY - JOUR

T1 - Comparison of the single channel and multichannel (multivariate) concepts of selectivity in analytical chemistry

AU - Dorkó, Zsanett

AU - Verbić, Tatjana

AU - Horvai, G.

PY - 2015/8/1

Y1 - 2015/8/1

N2 - Abstract Different measures of selectivity are in use for single channel and multichannel linear analytical measurements, respectively. It is important to understand that these two measures express related but still distinctly different features of the respective measurements. These relationships are clarified by introducing new arguments. The most widely used selectivity measure of multichannel linear methods (which is based on the net analyte signal, NAS, concept) expresses the sensitivity to random errors of a determination where all bias from interferents is computationally eliminated using pure component spectra. The conventional selectivity measure of single channel linear measurements, on the other hand, helps to estimate the bias caused by an interferent in a biased measurement. In single channel methods expert knowledge about the samples is used to limit the possible range of interferent concentrations. The same kind of expert knowledge allows improved (lower mean squared error, MSE) analyte determinations also in "classical" multichannel measurements if those are intractable due to perfect collinearity or to high noise inflation. To achieve this goal bias variance tradeoff is employed, hence there remains some bias in the results and therefore the concept of single channel selectivity can be extended in a natural way to multichannel measurements. This extended definition and the resulting selectivity measure can also be applied to the so-called inverse multivariate methods like partial least squares regression (PLSR), principal component regression (PCR) and ridge regression (RR).

AB - Abstract Different measures of selectivity are in use for single channel and multichannel linear analytical measurements, respectively. It is important to understand that these two measures express related but still distinctly different features of the respective measurements. These relationships are clarified by introducing new arguments. The most widely used selectivity measure of multichannel linear methods (which is based on the net analyte signal, NAS, concept) expresses the sensitivity to random errors of a determination where all bias from interferents is computationally eliminated using pure component spectra. The conventional selectivity measure of single channel linear measurements, on the other hand, helps to estimate the bias caused by an interferent in a biased measurement. In single channel methods expert knowledge about the samples is used to limit the possible range of interferent concentrations. The same kind of expert knowledge allows improved (lower mean squared error, MSE) analyte determinations also in "classical" multichannel measurements if those are intractable due to perfect collinearity or to high noise inflation. To achieve this goal bias variance tradeoff is employed, hence there remains some bias in the results and therefore the concept of single channel selectivity can be extended in a natural way to multichannel measurements. This extended definition and the resulting selectivity measure can also be applied to the so-called inverse multivariate methods like partial least squares regression (PLSR), principal component regression (PCR) and ridge regression (RR).

KW - Bias variance tradeoff

KW - Error inflation

KW - Interference

KW - Multivariate

KW - Selectivity

UR - http://www.scopus.com/inward/record.url?scp=84925791448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925791448&partnerID=8YFLogxK

U2 - 10.1016/j.talanta.2015.02.030

DO - 10.1016/j.talanta.2015.02.030

M3 - Article

VL - 139

SP - 40

EP - 49

JO - Talanta

JF - Talanta

SN - 0039-9140

M1 - 15403

ER -