16 July 2008
rrrrrrrigh...wait, what?
Statisticians speak of something called the Paradox of the False Positive. Here's how that works: imagine that you've got a disease that strikes one in a million people, and a test for the disease that's 99% accurate. You administer the test to a million people, and it will be positive for around 10,000 of them – because for every hundred people, it will be wrong once (that's what 99% accurate means). Yet, statistically, we know that there's only one infected person in the entire sample. That means that your "99% accurate" test is wrong 9,999 times out of 10,000!
Subscribe to:
Post Comments (Atom)
6 comments:
Cory Doctorow - Rare Events
http://www.guardian.co.uk/technology/2008/may/20/rare.events
aoleu, asta e exemplu de paradox pt adulti?
imi aminteste de paradoxurile cu care ne incuiam reciproc in scoala primara..
mi se pare absolut logic ca un test cu 99% reusita sa nu fie nici pe departe suficient de sigur pentru o boala cu frecventa de 1 la un milion.
nu stiu ce sa zic, exista paradoxuri pentru adulti?
:)
pai nu stiu acuma ce exemplu sa-ti dau dar mai pe zona mecanica newtoniana vs. mecanica cuantica decat pe zona 1 kg de puf vs 1 kg de plumb..
acuma daca tu te-ai incuiat cu asta...
nu e vorba ca mi-a stat mintea-n loc, paradoxurile sunt oricum o chestie mai degraba amuzanta.
intrebarea e: ai citit si articolul?
evident ca nu am citit.. dar citatul ala e absolut lamuritor. daca veneau statisticienii la mine cu paradoxul asta ii concediam pe toti. hai frate cu paradoxuri de-astea veniti voi la mine?
"You're fired!"
Post a Comment