Effect of constraints on precision of calibration analyses

Schwartz, Lowell M.

doi:10.1021/ac00292a061

Cited by 4 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meites et al claim that when linear regression is applied to data with error in the independent variable, the slope is underestimated, and not even weighted regression can correct this problem (CA50). He and Leary have presented several procedures for obtaining constrained calibration equations (CA32, CA49), but there is some controversy about the effect that this has on the precision of the calibration (CA63). Several methods have been compared for fitting highly non-linear atomic absorption spectroscopy calibration curves (CA51).…”

Section: Calibrationmentioning

confidence: 99%

Chemometrics

Ramos¹,

Beebe²,

Carey³

et al. 1986

Anal. Chem.

View full text Add to dashboard Cite

Section: Calibrationmentioning

confidence: 99%

Chemometrics

Ramos¹,

Beebe²,

Carey³

et al. 1986

Anal. Chem.

View full text Add to dashboard Cite

“…In this situation, a DL can be based on confidence limits (CL) around the calibration curve (7)(8)(9)(10)(11)(12)(13)(14),…”

mentioning

confidence: 99%

Effects of Analytical Calibration Models on Detection Limit Estimates

Owens

Bauer²,

Grant³

1987

ACS Symposium Series

View full text Add to dashboard Cite

Detection limit estimates derived from confidence bands around analytical calibration curves are highly dependent on the experimental design and on the statistical data treatment. Procedures are described for testing the linearity of data and whether the intercept differs significantly from zero. Insensitivity of the correlation coefficient for the evaluation of goodness of fit of calibration models is emphasized, unweighted linear models with an intercept often yield overly conservative detection limits. Frequently, an unweighted zero-intercept model is justified on both theoretical and statistical grounds. This model yields confidence bands and detection limits consistent with experiment. When the variance of signal measurements increases with concentration, more realistic confidence bands and detection limits are produced by weighting the data. Despite numerous papers dealing with the specification of analytical method detection limits (see, for example 1-6) r much disagreement remains about the choice of both experimental and computational procedures.In part, these disagreements appear to be related to the technical objectives of the experimenter. For example, a detection limit (DL) might be estimated from some multiple of the standard deviation of blank solution signals measured during a short time interval using a painstakingly optimized instrument.Such a DL estimate clearly provides useful information but it would be unrealistic to expect to maintain an equivalent DL during an extended analysis program with real samples.Unfortunately, these differences are frequently ignored, thereby encouraging unproductive controversy.It is important to remember that a DL is not an intrinsic property but rather, it is Current address:

show abstract

Chemometric methods in analytical research: A program of practical study

Colina¹,

Garnica²,

Palacios³

et al. 2005

J. Chemometrics

View full text Add to dashboard Cite

SUMMARYStatistical methods should be a means of reasoning and decision making integrated into research design in analytical chemistry and not merely an instrument for analysing empirical data. Consequently, full and rigorous use of these methods should be encouraged from the earliest stages of postgraduate training.In this paper a selection of well tried, straightforward procedures is given in the form of practical studies that give reliable, consistent and meaningful results. KEY WORDS Statistical proceduresPostgraduate practical studies in chemometrics Chemometrics has been accurately described as 'an interface between chemistry and mathematics'.' Such an interface will fulfil what is expected of it if the protocols for data transmission are concordant; otherwise, information cannot circulate through it freely.Obviously there are two facets to this question: the mathematical and the chemical. Our opinion on this matter is that the role of chemometrics is to strengthen the use of a basic knowledge of statistics not simply as a tool for interpreting empirical data but rather as a whole way of approaching experimental procedures and cause-effect relationships. Statistical methods are useful for analysing large amounts of data and for indicating reasonable decisions in cases of uncertainty. As a result, these methods constitute a theoretical tool to be used in close conjunction with experimentation. This point of view can and should be applied at various levels. The present work summarises our experience at the basic level, namely that at which an analytical chemist must start his statistical training with a view to designing empirical experiments. We shall not go into excessive detail but only give general guidelines as summarized in Figure 1.Any problem in analytical chemistry must be answered in the same chemical terms as which it was formulated. This is true not only in the case of choosing between alternative models but also when seeking an adequate description of a new situation produced by the results, which in turn are provided by a constantly evolving set of instruments. In both cases it can be foreseen that several successive formulations of a problem will be necessary so as to narrow it down in accordance with the experimental evidence. 0886-

show abstract

Effect of constraints on precision of calibration analyses

Cited by 4 publications

References 22 publications

Chemometrics

Chemometrics

Effects of Analytical Calibration Models on Detection Limit Estimates

Chemometric methods in analytical research: A program of practical study

Contact Info

Product

Resources

About