Polygraph Validity Research: A Summary of the meta – analytical survey of criterion accuracy of validated polygraph techniques

29th April 2015
Dr Ray Martin

 

 

 

 

It is the intention of this summary to provide decision – makers in business such as HR and Security managers with information as to the criterion validity/ accuracy of polygraph examinations in such a manner as to be easily understood. (This summary is taken from the Executive Summary as provided by the American Polygraph Association. A copy of the full report is available from its offices). This knowledge together with the selection of a reputable polygraphist, is essential to the successful use of the polygraph by private industry. Having said this I would urge the reader to take careful note of the ensuing article relating to the Integrity Assessment Programme.

It was some 8 years after the completion of my studies that the American Polygraph Association (APA) completed a report in late 2011. While not wanting to create the impression that my thesis was in any way the catalyst for said report, it most certainly has cleared up, to a certain extent, some misgivings I had expressed. This was in my opinion an absolutely essential intervention by the APA.

In 2007 the APA sought to adopt a Standard of practice for implementation on 1st January 2012. As mentioned the appropriate report was completed late in 2011 on the basis of 38 studies which were included in a meta – analysis. (A meta – analysis comprises statistical methods for contrasting and combining results from different studies in the hope of finding patterns/ disagreements in the results and thus provide a higher statistical power). The following points comprise the essence of this report:

  1. APA members are required to use validated Psychophysiological Detection of Deception examination techniques (PDDs). These PDDs had to meet certain levels of criterion accuracy which were stipulated for the various kinds of examinations. (Criterion accuracy is generally referred to as to the degree to which the examination result reflects that which the examination is purported to measure. This is a form of validity and must not be confused with reliability).
  2. The goal therefore was the elimination of the use of PDDs which were experimental, non – validated or un – standardized in field settings. It was felt that these had no place in field use where they would have a bearing on the lives of individuals, their integrity as well as community safety and national security. Thus the meta – analysis would show which present PDDs satisfied the requirements by assigning a level of criterion accuracy/ validity. It is important to know that there are numerous techniques and test question formats and that validity depends on the selection of proper test question format and the use of validated technique.
  3. The integrity of the research was of paramount importance and was placed ahead of any financial or personal interests of any developer of PDD testing who might be involved in the survey.
  4. Both field and laboratory studies were included. Field studies provide ecological validity and therefore are taken to have greater generalizability. (Ecological validity refers to the degree to which the experimental components match real – life conditions). Laboratory studies on the other hand, are able to control more variables and thus provide answers to causality and construct validity. (To what extent are cause and effect related and to what extent does the study measure what it is supposed to be measuring).
  5. Studies considered for the survey had to satisfy both qualitative and quantitative requirements and were only considered if they had been published by an accredited academic degree granting institution. All factors relevant to the survey were closely monitored.
  6.  According to the APA website Polygraph Validity Research (25/4/2015), “The combination of all validated PDD techniques, excluding outlier results, produced a decision accuracy of 87%….with an inconclusive rate of 13%. These findings were consistent with those of the National Research Council’s…”. These findings are confirmed by Polygraph( 2011, 40(4): 200) which goes on to add, “Data at the present time are (sic)sufficient to support the polygraph as highly accurate, but insufficient to support an assertion that PDD testing can provide perfect or near – perfect accuracy”.

What then is the significance of this exercise? Polygraph validity/ accuracy is again shown to reach levels of significance. However it must be noted that the validity of polygraph examination results rests in main with the polygraphist. This important factor will be examined and explained in an article which will follow the explanation of the Integrity Assessment Programme which serves as a noteworthy contributor to the use of the polygraph in employment context.

Dr. Ray Martin
29th April 2015