An investigation of proposed techniques for quantifying confidence in assurance arguments

The use of safety cases in certification raises the question of assurance argument sufficiency and the issue of confidence (or uncertainty) in the argument's claims. Some researchers propose to model confidence quantitatively and to calculate confidence in argument conclusions. We know of little evidence to suggest that any proposed technique would deliver trustworthy results when implemented by system safety practitioners. Proponents do not usually assess the efficacy of their techniques through controlled experiment or historical study. Instead, they present an illustrative example where the calculation delivers a plausible result. In this paper, we review current proposals, claims made about them, and evidence advanced in favor of them. We then show that proposed techniques can deliver implausible results in some cases. We conclude that quantitative confidence techniques require further validation before they should be recommended as part of the basis for deciding whether an assurance argument justifies fielding a critical system.