American Polygraph Association's statement regarding the validity of polygraphs. What does it mean?

[nopolycop]

The following is copied and pasted from the APA website:

"The American Polygraph Association has a compendium of research studies available on the validity and reliability of polygraph testing. The 80 research projects listed, published since 1980, involved 6,380 polygraph examinations or sets of charts from examinations. Researchers conducted 12 studies of the validity of field examinations, following 2, 174 field examinations, providing an average accuracy of 98%. Researchers conducted 11 studies involving the reliability of independent analyses of 1,609 sets of charts from field examinations confirmed by independent evidence, providing an average accuracy of 92%. Researchers conducted 41 studies involving the accuracy of 1,787 laboratory simulations of polygraph examinations, producing an average accuracy of 80%. Researchers conducted 16 studies involving the reliability of independent analyses of 810 sets of charts from laboratory simulations producing an average accuracy of 81%. Tables list the authors and years of the research projects, which are identified fully in the References Cited. Surveys and novel methods of testing are also mentioned. "


My question centers around the obvious discrepancy between the validity of field examinations and laboratory examinations.  Why so much discrepancy?

[1904]

Nopoly,

The APA is trying to convince the public that field testing research produces higher accuracy than lab studies, whereas the converse is true. But lab studies are bunkum.

[Barry_C]

I hope you're seasoning those feet.

The APA is trying to convince the public that field testing research produces higher accuracy than lab studies, whereas the converse is true. But lab studies are bunkum.

If the opposite is true, then lab studies are more accurate than field studies; yet, lab studies are "bunkum."

That makes perfect sense.

Real answer:  There are all kinds of studies in there - apples and oranges and pears.  You have to look inside the book to start crunching the numbers.  Some of those field studies are suspect, in my opinion.  For example, one study resulted in 100% accuracy (the technique's author / creator conducted the study).  (Before you go too crazy though, the NAS report included that study, which means it somehow "made the cut.")

[1904]

If the opposite is true, then lab studies are more accurate than field studies; yet, lab studies are "bunkum." That makes perfect sense.

I agree.
We're starting to sing from the same page.

I could actually get to like you at his rate.

[nopolycop]

I
Real answer:  There are all kinds of studies in there - apples and oranges and pears.  You have to look inside the book to start crunching the numbers.  Some of those field studies are suspect, in my opinion.  For example, one study resulted in 100% accuracy (the technique's author / creator conducted the study).  (Before you go too crazy though, the NAS report included that study, which means it somehow "made the cut.")

Okay, I'll narrow it down.  How is the accuracy of a field examination confirmed, to come up with the 98% accuracy quoted in the study?

[Sergeant1107]

It is also interesting to note that in the APA's response to the National Academy of Sciences research study, they dismissively write that the NAS study only used 57 of the more than 1000 studies available.  The implication is that the NAS did not avail itself of the bulk of the available research.

In their statement touting the accuracy of the polygraph, the APA cites 80 of the more than 1000 studies available...

The clear message, as absurd as it sounds, is that 57/1000 is a shoddy job of research, but 80/1000 is acceptable.

[1904]

It is also interesting to note that in the APA's response to the National Academy of Sciences research study, they dismissively write that the NAS study only used 57 of the more than 1000 studies available.  The implication is that the NAS did not avail itself of the bulk of the available research.

In their statement touting the accuracy of the polygraph, the APA cites 80 of the more than 1000 studies available...

The clear message, as absurd as it sounds, is that 57/1000 is a shoddy job of research, but 80/1000 is acceptable.

And that Sarge, is another big nail in the coffin of polygraph.
Nice One.

[Barry_C]

I think that is a reference to Norm Ansley's work done in about 1990.  The 80 research "projects" may refer to meta-analyses of several studies each, which could mean hundreds of studies.  It's been a while since I looked at that publication.  It's just numbers.  You've got to go to the studies for details or you're cheating yourself.  They probably need to update the numbers and/ or make it more clear.

They also include different types of tests.  Some are more accurate than others as has been pointed out here before.