Recent proposals for using the polygraph and similar devices in routine screening have been aimed at detecting deception in situations sometimes characterized by low base rates. Equations are developed that show that extraordinarily high levels of accuracy would be needed to detect infrequent deception. In this context, the debate over the accuracy of these methods is irrelevant; the accuracy needed to detect infrequent deception far exceeds the levels claimed by the most enthusiastic proponents of these detection techniques. The limits on the use of any particular test of deception can be determined by considering the base rate for deception and the proportion of the nondeceptive population that fails the test. When the base rate is less than. 10, these limits are extremely restrictive.
No takes yet. Share an insight, caveat, or question.
Kevin R. Murphy (1987) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: