Online Program Home
My Program

Abstract Details

Activity Number: 19
Type: Topic Contributed
Date/Time: Sunday, July 31, 2016 : 2:00 PM to 3:50 PM
Sponsor: Ad Hoc Advisory Committee on Forensic Science
Abstract #319350
Title: Biased by Design
Author(s): Clifford Spiegelman*
Companies: Texas A&M University
Keywords: design of experiments ; error rate ; misclassification ; blinding
Abstract:

Forensic practitioners need to provide justification for calling themself forensic scientists in court. A 2009 NRC report pointed out that except for nuclear DNA, nearly all other forensic practices are lacking the most basic fundamentals such as sound statistical practices. In a quest to substantiate unfounded claims for uniqueness and very low error rates, including identifications 'to a practical certainty' experiments are performed. These experiments, however, are biased to support claims using a number of devices that fool judges and jurors who are not versed in the mainstream science community. The devices used include, but are not limited to, the lack of double blinding, choosing too easy test cases, when compared to crime scene cases, flipping the null and alternative hypotheses, and performing experiments with little statistical power. This talk provides many examples.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association