Are Polygraph Tests Accurate?

Since the beginning of the polygraph in the early 1900s, there have been many advances in the technology and techniques used. With each development, the goal was to improve the accuracy of the device, although little research was done until a few decades ago. But today’s polygraph machines have been put to the test again and again, and increasingly evidence supports the validity of polygraph machines that record at minimum cardiovascular, respiratory, and electrodermal activity when the exam is done by a properly trained examiner following an accepted testing procedure and scoring system.

The American Polygraph Association has looked at the results of 80 research projects to determine the average accuracy of the tests. In 12 studies of the validity of field examinations, which followed 2,174 field examinations, the average accuracy was 98%. Eleven studies which looked at the reliability of independent analysis of 1,609 sets of charts from field examinations confirmed by independent evidence found an average accuracy of 92%. 41 studies which looked at the accuracy of 1,787 laboratory simulations found an average accuracy of 80%. And an average accuracy of 81% was found in 16 studies that looked at the reliability of independent analyses of 810 sets of charts from laboratory simulations.

Perhaps the most comprehensive review of polygraph testing was done by the US National Research Council (NRC) in 2003. After looking at 57 polygraph studies, it concluded that in populations of examinees such as those represented in the polygraph research literature, untrained in countermeasures, specific-incident polygraph tests can discriminate lying from truth telling at rates well above chance, though well below perfection. Just how much “above chance”? An analysis of the 30 polygraph data sets revealed an overall accuracy of 85 percent, and an analysis of seven field studies which involved specific incidents revealed a median accuracy of 89 percent. It also acknowledged that the examiner can affect the test’s accuracy, which is why it is so important to find someone who has the proper training and expertise.

Where the NRC report fails is that it considers all polygraph methods collectively, without taking into account if the proper machines were used, a trained expert performed the test, and the appropriate procedures were followed, which is why the American Polygraph Association is currently reviewing the studies of only the polygraph techniques that are scientifically supported. Both the NRC and APA came to similar conclusions about the mean accuracy of polygraph testing, but the APA has identified which approaches work best in order to help further improve the tests that its membership administers. The report from the APA will be available in January 2012.