QUANTIFYING UNCERTAINTY IN QUALITATIVE-ANALYSIS

The feasibility of adopting a consistent approach to the expression of uncertainties relating to identification is discussed. It is argued t hat qualitative analysis,can be viewed as a classification problem, th at it is at least as important as quantitative analysis and that infer ences 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 mo st suitable framework, providing for combination of separate items of evidence and implicitly allowing for both false positive and false neg ative probabilities in a single parameter. The chemical significance a nd practical evaluation of relevant probabilities are considered, and the applications and reporting of 'identification certainty' figures a re discussed.