Bayesians-Putting a prior on a Beta- HELP

Thread View: sci.math.stat

1 messages

[T] Back to Threads [V] Tree View [G] Group Articles

1 total messages Started by J.F.Murray Sun, 05 May 1991 19:52

#1003

Author: J.F.Murray
Date: Sun, 05 May 1991 19:52

28 lines
2050 bytes

Hi,
	I am a curious as to what is the common approach for putting a
prior on a Beta distribution.  I know that the  Beta distribution is the
defacto choice for a binomial distribution due to conjugacy .
What I wish to do now is to assume that I am sampling from a Beta
distributon and put some prior on that  Beta distribution. This is a  
Hierarchical Bayes situtation where I wish to represent my uncertainity on
the parameters of the Beta Distribution, say alpha and beta. What is
the best choice of distribution for this meta-prior?

Related question,
	In the Beta distribution we are usually interested in some random 
variable, say X.  Now the likelihood function for X given alpha and beta
is well known.  What is a likelihood function for the alpha and beta 
parameters given X.  Restating this

X ~ Beta(alpha,beta)  
     Likelihood(X |alpha,beta) =
 ((gamma(alpha+beta)/gamma(alpha)*gamma(beta))*X**(alpha-1)*(1-X)**(beta-1)

Ok, then what is 
	Likelihood(alpha,beta | X) = ???????????

I've struggled with this but only succeed in confusing myself.
I appreciate any help I can get on this problem.  Thanks in advance..
----------------------------------------------------------------------
jfmurray@vms2.macc.wisc.edu
jfmurray@WISCMACC.BITNET

Thread Navigation

This is a paginated view of messages in the thread with full content displayed inline.

Messages are displayed in chronological order, with the original post highlighted in green.

Use pagination controls to navigate through all messages in large threads.

Back to All Threads