The Student Room Group

Scroll to see replies

Reply 40
Cexy
Isn't this a simple application of Bayes' rule?

A = You get into Oxford
B = They interview the top 40%, and you get an interview
C = They interview the top 80%, and you get an interview

P(A|B) = P(A)P(B|A)/P(B)
P(A|C) = P(A)P(C|A)/P(C)

I think we can agree that P(B|A)=P(C|A)=1, and that P(B)<P(C). Therefore P(A|B)>P(A|C).


doesnt that assume that they pick candidates at random or just the top X amount so as to fill their course...surely if all 40% were bad neither of them would get an offer?
Reply 41
No, I don't think it makes any unjustified assumptions.

Of course, whether Oxford interviews 40% or 80% of its applicants doesn't make a blind bit of difference to whether a specific person gets in or not, but if all you know about a person is that they got an interview, then they're more likely to get in if the university are interviewing fewer people (obviously).

Latest

Trending

Trending