MathOverflow will be down for maintenance for approximately 3 hours, starting Monday evening (06/24/2013) at approximately 9:00 PM Eastern time (UTC-4).
0

1

How can we apply Bayes theorem on histogram ?

flag
1 
 Search "Dirichlet processes" or "Bayesian density estimation". – R Hahn Oct 1 at 0:49
4 
 Apply the theorem to do what? – Yemon Choi Oct 1 at 0:55
I am looking specially for histogram . but i did not find that in the questions related to Bayesian density estimation. – tina123 Oct 1 at 0:55
@yemon Well , using Bayesian formula , we can show that posterior probability which is proportional to the density value. So i am interested in Bayesian formula on histogram . – tina123 Oct 1 at 0:58
2 
 Dear tina123, this question needs some amending. Please read the howtoask page and then edit your question. – Theo Johnson-Freyd Oct 1 at 1:20

closed as not a real question by Yemon Choi, Qiaochu Yuan, Douglas Zare, algori, Steven Landsburg Oct 1 at 1:21

1 Answer

1

You may treat the histogram as observations arising from a multinomial distribution. The conjugate prior for a multinomial likelihood is a Dirichlet distribution. If you want to allow the number of bins to grow as you collect more data, this leads to a Dirichlet process prior, as I mentioned in my early comment.

link|flag

Not the answer you're looking for? Browse other questions tagged or ask your own question.