PerspectiveQuantifying uncertainty in qualitative analysis

Abstract

The feasibility of adopting a consistent approach to the expression of uncertainties relating to identification is discussed. It is argued that qualitative analysis can be viewed as a classification problem, that it is at least as important as quantitative analysis and that inferences drawn from qualitative tests should take relevant uncertainties into account. A brief review of systems of reasoning under uncertainty is presented, and it is concluded that Bayes’ theorem provides the most suitable framework, providing for combination of separate items of evidence and implicitly allowing for both false positive and false negative probabilities in a single parameter. The chemical significance and practical evaluation of relevant probabilities are considered, and the applications and reporting of ‘identification certainty’ figures are discussed.

References

1. M. Viktorin, LaborPraxis, 1995, 19, 80.
2. P. I. Laferty, J. Forensic Sci., 1994, 39, 261.
3. L. B. Rogers, Anal. Chem., 1990, 62, 703A.
4. T. Cairns, E. G. Siegmund, T. L. Barry and G. Petzinger, Rapid Commun. Mass. Spectrom., 1990, 4, 58.
5. A. F. Weston, Chem. Eng., 1984, 91, 54.
6. Guide To The Expression Of Uncertainty In Measurement, ISO, Geneva, 1993.
7. Quantifying Uncertainty in Analytical Measurement, Eurachem working group on uncertainty in chemical measurement (12 members). LGC, Middlesex, UK, 1995.
8. Accuracy (trueness and precision) of measurement methods and results, ISO, Geneva, 1995, ISO 5725:1994.
9. W. Horwitz, Pure Appl. Chem., 1988, 60, 855.
10. G. Den Boef and A. Hulanicki, Pure Appl. Chem., 1983, 55, 553.
11. International Union of Pure and Applied Chemistry, Compendium of Analytical Nomenclature, Blackwell Scientific Publications, Oxford, 1987.
12. A. M. van Ginneken and A. W. M. Smeulders, Anal. Quant. Cytol. Histol., 1991, 13, 93.
13. G. Gettinby, M. Peterson and N. Watson, J. Forensic Sci. Soc., 1993, 33, 212.
14. C. G. G. Aitken and D. A. Stoney, The Use of Statistics in Forensic Science, Ellis Horwood, Chichester, 1991.
15. C. G. G. Aitken, Statistics and the Evaluation of Evidence for Forensic Scientists, Wiley, Chichester, 1995.
16. D. A. Berry, in DNA on Trial: Genetic Identification and Criminal Justice, Cold Spring Harbor Laboratory Press, Plainview, NY, 1992.
17. I. W. Evett, J. Forensic Sci. Soc., 1986, 26, 3.
18. See, for example, I. W. Evett and P. Gill, Electrophoresis, 1991, 12, 226.
19. R. Neuböck, W. Wegscheider and M. Otto, Microchem. J., 1992, 45, 343.
20. S. D. Ferrara, L. Tedeschi, G. Frison, G. Brusini, F. Castagna, B. Bernardelli and D. Soregaroli, J. Anal. Toxicol., 1994, 18, 278.
21. B. G. Buchanan and E. H. Shortlife, Rule Based Expert Systems—The MYCIN experiments of the Stanford Heuristic Programming Project, Addison Wesley, Menlo Park, CA, 1985.
22. E. J. Horwitz, D. E. Heckerman, B. N. Nathwani and L. M. Fagan, in Proceedings of the First Conference on Artificial Intelligence Application, IEEE Computer Society, New York, 1984, p. 630.
23. L. C. Van der Gaag, Int. J. Expert Syst., 1994, 7, 289.
24. D. J. Ramsbottom, M. J. Adams, J. Sumiga and J. Carroll, Chemom. Intell. Lab. Syst., 1993, 19, 53.
25. Q. Dan and J. Dudeck, Med. Inf., 1992, 17, 87.
26. E. H. Forman, Expert Syst. Appl., 1992, 4, 259.
27. C. G. Georgakopoulos, M. Statheropoulos, J. Kontoyannakos and G. Parissakis, J. Anal. Appl. Pyrol., 1995, 34, 29.
28. P. B. Harrington, T. E. Street, K. J. Voorhees, F. R. Brozolo and R. W. Odom, Anal. Chem., 1989, 61, 715.
29. L. A. Zadeh, Information and Control, 1965, 8, 338.
30. M. Otto, Anal. Chem., 1990, 62, 797.
31. B. Walczak, E. Bauer-Wolf and W. Wegscheider, Mikrochim. Acta, 1994, 113, 153.
32. G. Shafer, J. Am. Stat. Assoc., 1982, 77, 325.
33. W. G. De Ruig, G. Dijkstra and R. W. Stephany, Anal. Chim. Acta, 1989, 223, 277.
34. L. A. Currie and W. Horwitz, Analusis, 1994, 22, M24.
35. J. Fleming, Anal. Proc., 1995, 32, 31.