EclectEcon

Economics and the mid-life crisis have much in common: Both dwell on foregone opportunities

C'est la vie; c'est la guerre; c'est la pomme de terre . . . . . . . . . . . . . email: jpalmer at uwo dot ca


. . . . . . . . . . .Richard Posner should be awarded the next Nobel Prize in Economics . . . . . . . . . . . .

Sunday, July 03, 2005

Michael Jackson, Type I, and Type II Errors

The standard of proof in criminal cases is "guilty beyond a reasonable doubt" because society has decided we would rather make more of what statisticologists call type II errors (free the guilty) if required to do so as a trade-off to reduce the number of type I errors (convict the innocent). Here, the null hypothesis is that the defendant is not guilty.

Presumably, based on media accounts, at least some of the jurors thought that Michael Jackson was a paedophile but that the prosecution had not made the case beyond a reasonable doubt that he had engaged in any criminal behaviour.

The opposite happened in Scotland recently [h/t to Brian Ferguson].

A MAN who slit his neighbour's throat and set fire to his flat in the mistaken belief that he was a paedophile was jailed for life yesterday and ordered to serve at least eight years.

Angus Mackinnon, 53, "snapped" and killed Derek Gourley, 60, after being invited to watch what he thought were child pornography videos. ...

Police later established the tapes did not show children.
Talk about big-time Type I errors!

I know of several people who would like to turn Mr. Mackinnon loose on some other members of society.
 
Who Links Here