Email discussion lists for the UK Education and Research communities

## BUGS@JISCMAIL.AC.UK

#### View:

 Message: [ First | Previous | Next | Last ] By Topic: [ First | Previous | Next | Last ] By Author: [ First | Previous | Next | Last ] Font: Proportional Font
 LISTSERV Archives BUGS Home BUGS 2006

#### Options

Subject:

help needed with basic bayesian updating

From:

Zhang, Yong-Ping

Date:

Fri, 14 Jul 2006 00:54:14 -0500

Content-Type:

text/plain

Parts/Attachments:

 text/plain (52 lines)
 ```Dear All, I am wondering if WinBUGS is the one that I can use to do the very basic Bayesian updating? I mean something like "if the prior distribution of a parameter is gamma, and new data has poisson distribution, then the posterior distribution of the parameter is another gamma". However,in all of the examples of WinBUGS, people are trying to model the relationship between a parameter theta(which is a parameter in the distribution of a variable y) and other variables x. In my case, I just want to update the parameter without complex modelling. In the following model I have passed the "check model" but when I load the data, it shows "expected variable name". Context: here y is a variable called "trip distance per person per day".Suppose I have old data yi, from which Crystal Ball gives a good fitting distribution of beta(alpha=5.06,beta=18.59).Based on it,I assume the prior distributions of alpha is normal(5.06,0.001) and beta~normal(18.59,0.001). Now I have some new data yi(new),which I suppose comes from a population of another beta distribution (i.e.,the function to build likelihood). I want to know what the updated distributions of alpha and beta are. Can I use the means of updated alpha and beta to get the updated distribution of variable y. Your help to me is highly appreciated. Regards, Yongping Zhang model    {       for (i in 1:N) {         y[i] ~ dbeta(alpha, beta)           }          alpha ~ dnorm(5.06,0.001)          beta ~ dnorm(18.59,0.001)         } list (y=c(1.00,1.50,8.50,3.50,8.67,6.00,4.00,4.00,4.00,7.00,8.00,4.25,8.33), N=13)#Data list (alpha=5, beta=18) # intials ------------------------------------------------------------------- This list is for discussion of modelling issues and the BUGS software. For help with crashes and error messages, first mail [log in to unmask] To mail the BUGS list, mail to [log in to unmask] Before mailing, please check the archive at www.jiscmail.ac.uk/lists/bugs.html Please do not mail attachments to the list. To leave the BUGS list, send LEAVE BUGS to [log in to unmask] If this fails, mail [log in to unmask], NOT the whole list ```