People v. Collins
After a mathematics instructor testified about the multiplication rule for probability, though ignoring conditional probability, the prosecutor invited the jury to consider the probability that the accused (who fit a witness's description of a black male with a beard and mustache and a Caucasian female with a blond ponytail, fleeing in a yellow car) were not the robbers, suggesting that they estimated the odds as:
|Black man with beard||1 in 10|
|Man with mustache||1 in 4|
|White woman with pony tail||1 in 10|
|White woman with blond hair||1 in 3|
|Yellow motor car||1 in 10|
|Interracial couple in car||1 in 1,000|
The California Supreme Court set aside the conviction, criticizing the statistical reasoning for ignoring dependencies between the characteristics, e.g., bearded men commonly sport mustaches, and for drawing an incorrect statistical inference. This mistaken inference, commonly called the prosecutor's fallacy, incorrectly equates the probability that a random defendant has certain traits with the chance that the defendant is guilty. The court noted that the correct statistical inference would be the probability that no other couple who could have committed the robbery had the same traits as the defendants given that at least one couple had the identified traits. The court noted, in an appendix to its decision, that using this correct statistical inference, even if the prosecutor's statistics were all correct and independent as he assumed, the probability that the defendants were innocent would be over 40%.
The court asserted that mathematics, "...while assisting the trier of fact in the search of truth, must not cast a spell over him." In particular, the court expressed its concern that complex mathematics would distract the jury from weighing the credibility of witnesses and the reasonableness of their doubts. The court also expressed concern that if mathematics became common tools for prosecutors that there would not be enough defense attorneys skilled at mathematics to put on a skilled defense.
- People v. Collins, 68 Cal.2d 319 (California Supreme Court March 11th, 1968) ("Mathematics, a veritable sorcerer in our computerized society, while assisting the trier of fact in the search for truth, must not cast a spell over him.").
- Tribe, Laurence H. (April 1971). "Trial by Mathematics: Precision and Ritual in the Legal Process". Harvard Law Review. 84 (6): 1329–1393. doi:10.2307/1339610. hdl:10822/763743. JSTOR 1339610.
- Finkelstein, Michael O.; Fairley, William B. (January 1970). "A Bayesian Approach to Identification Evidence". Harvard Law Review. 83 (3): 489–517. doi:10.2307/1339656. JSTOR 1339656.
- Kreith, Kurt (August 1976). "Mathematics, social decisions and the Law". International Journal of Mathematical Education in Science and Technology. 7 (3): 315–330. doi:10.1080/0020739760070308. ISSN 0020-739X – via Taylor & Francis.
- Schneps, Leila; Colmez, Coralie (2013). "Math error number 2: unjustified estimates. The case of Janet Collins: hairstyle probability". Math on trial : how numbers get used and abused in the courtroom. New York: Basic Books. ISBN 978-0-465-03292-1. OCLC 808421296.
- "People v. Collins, 68 Cal. 2d 319 - Cal: Supreme Court 1968". Supreme Court of California – via Google Scholar.