Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Notice: We are no longer accepting new posts, but the forums will continue to be readable.

Topic: EFD vs EWD in a Naive Bayes Classifier
Replies: 7   Last Post: Sep 24, 2008 9:33 AM

 Messages: [ Previous | Next ]
 Glen Low Posts: 41 Registered: 12/13/04
Re: EFD vs EWD in a Naive Bayes Classifier
Posted: Sep 19, 2008 9:08 PM

On Sep 19, 8:41 pm, Peter <peterp...@hotmail.com> wrote:
> I do not know this particular application, but consider that, to keep frequencies equal, high-density events will be binned in smaller intervals. So probability is inversely related to the length of the interval (as in |a2-a1|) that your observation p falls in.

Define pi = P(p in bin i), li = length of interval i, ni = instances
in bin i, k = constant of proportionality
Then

pi = k * ni / li
sum(pi) = sum (k * ni / li) = 1
1 = k * sum (ni / li)
k = 1 / sum (ni / li)

therefore pi = ni / (li * sum (ni / li))

I suppose this makes sense from a mathematical derivation point of
view, I just find it hard to see the intuitive view of it.

Date Subject Author
9/19/08 Glen Low
9/19/08 Peter
9/19/08 illywhacker
9/19/08 Glen Low
9/20/08 Peter
9/19/08 Glen Low
9/20/08 Peter
9/24/08 illywhacker