Bayesian bias in forensics (Dr. Roger Koppl, Fairleigh Dickinson University)

The current organization of forensic science induces biases in the conduct of forensic science even if forensic scientists are perfectly rational Bayesians. We recognize that they are not, and that "irrationalities" of human cognition may induce other biases or strengthen the biases we identify. Assuming forensic examiners are flawless Bayesians, however, helps us to identify structural sources of error that we might otherwise have undervalued or missed altogether. The authorities – police and prosecutors – implicitly convey information to forensic examiners by their very decision to submit samples for testing. This information induces the examiners to update their prior assessments of the likelihood of guilt, and their updated beliefs are reflected in a greater tendency to announce a "match" that incriminates the suspect. Forensic results are in a sense "contaminated" by the prosecution and thus do not provide jurors with an independent source of information.

Materials

Presentation

G Whitman and R Koppl. Bayesian Bias in Forensics. June 2008.