Thread: Q19
View Single Post
  #6  
Old 09-16-2012, 11:44 PM
fgpancorbo fgpancorbo is offline
Senior Member
 
Join Date: Jul 2012
Posts: 104
Default Re: Q20

Quote:
Originally Posted by yaser View Post
(emphasis added)
It should be based on rater than out of. A source of confusion here is that f is a probability, but then we have a probability distribution over f. Let us just call f the fraction of heart attacks in the population. Then the problem is addressing the probability distribution of that fraction - Is the fraction more likely to be 0.1 or 0.5 or 0.9 etc. The prior is that that fraction is equally likely to be anything (uniform probability). The problem then asks how this probability is modified if we get a sample of a single patient and they happen to have a heart attack.
I see. If my understanding is correct, I think that I can safely assume that P(\mathcal{D}|h=f), in which \mathcal{D} is made of a single random variable say x, has a Bernoulli distribution with parameter p=f. Is that right?
Reply With Quote