The Lie Detector Test – How Accurate?
Posted by Blood Tests | Posted in Biometric Testing, Blood Tests | Posted on 06-03-2011
Tags: Blood Test, Blood Tests
0
Is the lie detector test (polygraph) accurate? That depends on who you ask. Studies show results of all sorts. A recent Department of Defense Polygraph Institute study, found one experiment in which less than 37% of test takers who were non-deceptive were classified as such. Others were either classified as “deceptive” (false-positives) or “inconclusive.” Would you really want to “prove” your innocence using a test with those odds?
The APA (American Polygraph Association) says on their web site that the problem is one of differing methods of measuring accuracy. Polygraph critics, they say, “who often don’t understand polygraph testing, classify inconclusive test results as errors.” An “inconclusive” result is not an error, they say, but I imagine that if you are accused of murder, and you are innocent, you might want something more accurate than “inconclusive” from your polygraph test. The APA will not call it a lie detector test, by the way, even though detecting lies is what it is supposed to do.
One APA explanation: “If 10 polygraph examinations are administered and the examiner is correct in 7 decisions, wrong in 1 and has 2 inconclusive test results, we calculate the accuracy rate as 87.5% (8 definitive results, 7 of which were correct.) Critics of the polygraph technique would calculate the accuracy rate in this example as 70 percent, (10 examinations with 7 correct decisions.)” This argument is not entirely unreasonable, since there are several ways to measure accuracy.
What’s interesting here, is that even in an argument from the biggest promoters of the polygraph, the example given is of of 87.5% accuracy, and 20% “inconclusive” results. This means that of a 100 people tested in a murder case, about 10 innocent people would be found to be “lying,” and 20 with an “inconclusive” reading. Those with inconclusive results might include both murderers and innocent people.
Lets look at this another way. Of a 100 murderers, 10 would be found to be telling the truth, and 20 would have inconclusive results from their lie detector results. In other words, out of 100 murders, 30 wouldn’t be identified, according to the accuracy assumed in the example above.
Now let’s consider the APA method again, with a new example. Suppose we question 100 innocent people about a crime, and just one was found to be telling the truth, while the other 99 tests had “inconclusive” results. A relatively useless test, don’t you think? It correctly identifies just 1 out of 100 innocent people. It leaves a cloud of suspicion over the other 99 people. However, the accuracy would be 100% if we measure the results the way the American Polygraph Association does.
The lie detector test isn’t considered science by most researchers. On the APA web site, you are able to find a little about the scientific evidence for the polygraph. A small excerpt: “Scientists conducted 41 studies involving the accuracy of 1,787 laboratory simulations of polygraph examinations, producing an average accuracy of 80 percent. Scientists conducted 16 studies involving the reliability of independent analyses of 810 sets of charts from laboratory simulations producing an average accuracy of 81 percent.”
Think about this for a moment. Is 80% supposed to be accurate enough?! Such a test would identify 200 out of a thousand innocent job applicants as liars, and many more as possible liars (“inconclusive”). Is this lie detector test really something that should be encouraged? Now you are able to understand item number 7 from the APAs “Checklist for the Polygraph Examiner”: “Carry a minimum of $50,000 or equivalent professional liability coverage.”

