Visualizing Trials with Large DNA Databases
17 Pages Posted: 17 Apr 2015 Last revised: 9 May 2015
Date Written: April 15, 2015
This essay seeks to help the reader follow the analysis by Ayres and Nalebuff of the use of probability theory in assessing DNA evidence drawn from large databases. I first guide the reader through visualizing a simpler paradox of probability theory: the rare disease test. I then offer a visual understanding of their paradigmatic setting: DNA evidence from a large database identifies an individual, but a deceased prime suspect also exists whose DNA is not available. A third unknown perpetrator whose DNA is not in the database is also a possibility. Consider the three possible scenarios. In the first scenario, the deceased prime suspect is the perpetrator, and the DNA test produces a false positive identification. In the second scenario the unknown perpetrator is guilty, and again the court observes a false positive. The third scenario has the perpetrator in the database, and the court observes a true positive. Effectively, the court needs to ascertain the probability of the third scenario, which turns out to be highly likely. This approach makes visible the possibility of a false positive after a false negative.
Keywords: DNA evidence, probability theory, visualization, probability tree
JEL Classification: K14, K41
Suggested Citation: Suggested Citation