People v. Collins

"The People of the State of California v. Collins " ( people of California against Collins ) was a jury award in 1968, which use (and abuse) operational statistics on a well known manner.

Malcolm Ricardo Collins and Janet Louise Collins were convicted because they had stolen about $ 35 from a frail lady. They laid thereupon an appeal and were acquitted, when the Supreme Court of California, the considerations of the trial court criticized harshly.

Process in the first instance

Eyewitness of a robbery in Los Angeles reported that the perpetrators were a dark-skinned man with a beard and mustache, and a fair-skinned woman with blond, tied in a ponytail hair. They had fled in a yellow car.

According to statements made by a " mathematics instructor " a California Colleges on the multiplication rule of probability theory the prosecutor invited the jury, the probability that the defendant is not the bank robber were to assess. Although the " instructor " did not address the so-called conditional probability, the prosecutor was sure that the following assumptions were correct:

The jury found both defendants guilty. because

Results, they concluded that the defendants would inevitably be the culprit - since the probability that there is another, all the witnesses give descriptions fulfilling pair, is very small in Los Angeles - namely one to twelve million. The fact that the victim of the crime to justice the perpetrators could not be clearly identified and that the details of their clothing disagreed, played for the jury a lesser role than the seemingly impressive numbers.

Discussion

From a scientific perspective, the statistical derivation of the expert has been criticized because it neglected the existence of related or dependent characteristics - two probabilities may only be multiplied if they are completely independent. So, for example, carries a man with a beard is more likely a mustache as a beardless men. On the other hand, carry more women than men ponytails. So you meet a person with a ponytail, the person is often female. Had the probabilities for the cases " ponytail " and "female " independent, so you would have to find the same number of women and men among a random sample of ponytail -bearing people.

Another point of discussion of the case was the use of probability theory to the determination of guilt. Even with a correctly executed probability theory the risk of fallacy is always given. It is also unclear at what level of probability can be assumed that a debt.