Voodoo science – continued

We previously commented on an issue of voodoo science, and more on voodoo science, and the National Research Counsel report on the future of forensics. The promoters of this piece of voodoo — a voice stress analyser — convinced law enforcement to fund and buy their expensive machine and methods for using voice stresses to tell if a suspect was lying. A number of reputable people published or sought to publish peer reviewed critiques. Rather than rebut with more peer reviewed research the owners of the company sued. That’s right, rather than conduct the discussion in the research laboratory and through peer reviewed articles and research, they sought to close down critics through lawsuits. Also, they persuaded the supposedly neutral peer reviewed journal, the International Journal of Speech Language and the Law, to withdraw the critical commentary. The critique is still available due to the internet — an alert reader captured the article before it was removed from the journal’s website. The company had received government funding.

Well here is the next of likely several more shoes to fall on this supposed reliable technology. It continues to be put through its own stress tests.

James D. Harnsberger, Harry Hollien, Camilo A. Martin, and Kevin A. Hollien (in press) Stress and Deception in Speech: Evaluating Layered Voice Analysis, Journal of Forensic Sciences.

The results showed that the “true positive” (or hit) rates for all examiners averaged near chance (42–56%) for all conditions, types of materials (e.g., stress vs. unstressed, truth vs. deception), and examiners (scientists vs. manufacturers). Most importantly, the false positive rate was very high, ranging from 40% to 65%. Sensitivity statistics confirmed that the LVA system operated at about chance levels in the detection of truth, deception, and the presence of high and low vocal stress states.

BLUF, according to this independent research the technology is as reliable as chance, that is, you can toss a coin and get the same or likely the same answer.

The JFS is THE journal for forensic science. It is published by the American Academy of Forensic Science. It is one of THE most respected peer reviewed journals for forensic science.

So now, when can the Journal of Forensic Science expect to be sued?