> -----Original Message-----
> From: Thomas, Andrew
> Sent: Thursday, July 05, 2001 1:03 PM
> To: [log in to unmask]
> Subject: multivariate normal with missing data
>
> WinBUGS does not allow the use of a multivariate distribution with some of
> its components data and the others to be sampled from.
>
> There are two cases to consider the MVN as prior and as likelihood. For a
> hierarchical model the same MVN could occur in both context.
>
> In principle it should be possibel to teach WinBUGS to consider such mixed
> MVN as a series of univariate normals when used as a prior. The difficulty
> is in keeping track of what forms the likelihood for this prior.
> At present if the first component of a conjugate multivariate distibution
> is unkown a likelihood is constructed for the multivariate node in the
> form of a list of nodes. So this would need changing.
>
> I will see what can be done.
>
>
> Regards
>
> Andrew
-------------------------------------------------------------------
To mail the BUGS list, mail to [log in to unmask]
You can search old messages at www.jiscmail.ac.uk/lists/bugs.html
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
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]
|