>-<model 1>----
># model
>model {
> a0 ~ dnorm(10,1)
> b0 ~ dnorm(10,1)
> c0 <- a0 + b0
> d0 ~ dnorm(c0,1000000)
>}
># data
>list(d0=75)
This 'trick' for handling observations on logical nodes can be really
dangerous. Convergence will be very very slow, as shown in this case, as
each node to be sampled is almost precisely constrained by the
others. This is a problem with single-node updating. Even with joint
updating, identifiability is entirely imposed by the prior so the precise
form of the prior distribution will be very influential.
David
(However in this particular example the properties may be improved by
having data that matches the model)
-------------------------------------------------------------------
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
|