What is the current truth about polygraph lie detection?

With reference to the continued debate about polygraph lie detection, this article applies standard criteria of scientific validity to the most common and influential polygraph procedure, the Control Question Test (CQT). Apart from the CQT's coding objectivity, which is satisfactory, the remaining validity criteria are neither met nor even tested seriously. Published evidence does not allow for item analyses and therefore does not speak to internal consistency and the assumed existence and invariance of the measured construct. The underlying decision model remains unspecified and untested, reflecting lack of construct validity. Optimistic estimates of the CQT's predictive validity suffer from a serious sampling-bias problem. And the notion of incremental validity is hardly considered at all. Due to ethical and professional reasons, it is argued that a fair and responsible appraisal of polygraph testing should clearly reveal this lack of validity, rather than seeking a 2-sided compromise. This article is based on a review that led a German Supreme Court to abandon the CQT from penal procedures.