Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

When would statistics support a suspicion of foul play? The scarcity of some occurrence isn't proof against it.


Figure out a prior probability of foul play, figure out the probability of a car bursting into flames on impact, plug the result into Bayes' theorem, and you get the relative likelihoods.

No, scarcity isn't proof against, but it is evidence. A lot of people are talking nonstop about the rarity of cars bursting into flames as evidence against that interpretation, while ignoring the even greater rarity of journalists being murdered by the US government.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: