A two-component model for measurement error in analytical chemistry

David M Rocke, Stefan Lorenzato

Research output: Contribution to journalArticle

144 Citations (Scopus)

Abstract

In this article, we propose and test a new model for measurement error in analytical chemistry. 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. We use maximum likelihood estimation and apply the technique to toluene by gas-chromatography/mass-spectrometry and cadmium by atomic absorption spectroscopy.

Original languageEnglish (US)
Pages (from-to)176-184
Number of pages9
JournalTechnometrics
Volume37
Issue number2
DOIs
StatePublished - 1995

Fingerprint

Component Model
Measurement errors
Measurement Error
Chemistry
Chemical analysis
Standard deviation
Atomic spectroscopy
Gas Chromatography
Absorption Spectroscopy
Maximum likelihood estimation
Mass Spectrometry
Absorption spectroscopy
Maximum Likelihood Estimation
Model
Gas chromatography
Cadmium
Mass spectrometry
Toluene
Multiplicative
Zero

Keywords

  • Atomic absorption spectroscopy (AAS)
  • Coefficient of variation
  • Detection limit
  • Gas-chromatography/mass-spectrometry (GC/MS)
  • Maximum likelihood
  • Quantitation level

ASJC Scopus subject areas

  • Modeling and Simulation
  • Applied Mathematics
  • Statistics and Probability

Cite this

A two-component model for measurement error in analytical chemistry. / Rocke, David M; Lorenzato, Stefan.

In: Technometrics, Vol. 37, No. 2, 1995, p. 176-184.

Research output: Contribution to journalArticle

Rocke, David M ; Lorenzato, Stefan. / A two-component model for measurement error in analytical chemistry. In: Technometrics. 1995 ; Vol. 37, No. 2. pp. 176-184.
@article{ef53cacc11b745bfab80fce46928b1f8,
title = "A two-component model for measurement error in analytical chemistry",
abstract = "In this article, we propose and test a new model for measurement error in analytical chemistry. 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. We use maximum likelihood estimation and apply the technique to toluene by gas-chromatography/mass-spectrometry and cadmium by atomic absorption spectroscopy.",
keywords = "Atomic absorption spectroscopy (AAS), Coefficient of variation, Detection limit, Gas-chromatography/mass-spectrometry (GC/MS), Maximum likelihood, Quantitation level",
author = "Rocke, {David M} and Stefan Lorenzato",
year = "1995",
doi = "10.1080/00401706.1995.10484302",
language = "English (US)",
volume = "37",
pages = "176--184",
journal = "Technometrics",
issn = "0040-1706",
publisher = "American Statistical Association",
number = "2",

}

TY - JOUR

T1 - A two-component model for measurement error in analytical chemistry

AU - Rocke, David M

AU - Lorenzato, Stefan

PY - 1995

Y1 - 1995

N2 - In this article, we propose and test a new model for measurement error in analytical chemistry. 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. We use maximum likelihood estimation and apply the technique to toluene by gas-chromatography/mass-spectrometry and cadmium by atomic absorption spectroscopy.

AB - In this article, we propose and test a new model for measurement error in analytical chemistry. 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. We use maximum likelihood estimation and apply the technique to toluene by gas-chromatography/mass-spectrometry and cadmium by atomic absorption spectroscopy.

KW - Atomic absorption spectroscopy (AAS)

KW - Coefficient of variation

KW - Detection limit

KW - Gas-chromatography/mass-spectrometry (GC/MS)

KW - Maximum likelihood

KW - Quantitation level

UR - http://www.scopus.com/inward/record.url?scp=0001072413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0001072413&partnerID=8YFLogxK

U2 - 10.1080/00401706.1995.10484302

DO - 10.1080/00401706.1995.10484302

M3 - Article

AN - SCOPUS:0001072413

VL - 37

SP - 176

EP - 184

JO - Technometrics

JF - Technometrics

SN - 0040-1706

IS - 2

ER -