Re: bayesian update hyperparameters
 From: "Anon." <bob.ohara@xxxxxxxxxxx>
 Date: Fri, 13 Jul 2007 21:13:22 +0300
erehwon wrote:
Hello,Prior for which parameters? Obviously not the probabilities (unless m=2), as they are constrained to add up to 1.
If I'm determining a posterior (multinomial) distribution based on
observed data, and if the chosen prior distribution is just the uniform
distribution, then there aren't any hyperparameters right?
(I have seen that when the prior distribution is Dirichlet, then there is aNo, the Dirichlet has as many parameters as there are classes.
single hyperparameter, but I believe this is different scenario...but I'm
not entirely sure.)
The Dirichlet is the conjugate prior for the multinomial, and setting alpha=1 for all classes is equivalent to using a uniform distribution.
Bob

Bob O'Hara
Department of Mathematics and Statistics
P.O. Box 68 (Gustaf Hällströmin katu 2b)
FIN00014 University of Helsinki
Finland
Telephone: +3589191 51479
Mobile: +358 50 599 0540
Fax: +3589191 51400
WWW: http://www.RNI.Helsinki.FI/~boh/
Blog: http://deepthoughtsandsilliness.blogspot.com/
Journal of Negative Results  EEB: www.jnreeb.org
.
 FollowUps:
 Re: bayesian update hyperparameters
 From: Joel
 Re: bayesian update hyperparameters
 References:
 bayesian update hyperparameters
 From: erehwon
 bayesian update hyperparameters
 Prev by Date: Re: A simple QUIZ
 Next by Date: Re: A simple QUIZ
 Previous by thread: bayesian update hyperparameters
 Next by thread: Re: bayesian update hyperparameters
 Index(es):
Relevant Pages
