I am new to WinBUGS, and pretty new to Bayesian analysis. I am trying to write code to accomplish a mixed model with 98 fixed effect parameters and 15 random effects parameters. I have two problems:
1. I have generated the X (fixed) and Z (random) matrices in SAS, as well as priors for the beta vector (coeff. of X) and Lambda matrix (var/cov matrix for the distribution of beta). I need to get these saved SAS datasets into WinBUGS.
2. The bigger issue is how to write this model in WinBUGS. I have looked around and can only find examples written in scalar form, which seems unnecessarily tedious for this setting.
Model: Y=X*beta + Z*gamma + epsilon
beta ~ MVN (Beta0, Lambda)
gamma ~ MVN (0, Gamma) --> Gamma~inverse Wishart
epsilon ~ MVN (0, Sigma) --> Sigma=diag(Sigma_i) where Sigma_i=sigma_i^2*I (naturally, I=identity)
I'm sure that this is pretty straightforward for some of you, and I greatly appreciate any help that can be provided.
- Sam Wilcock
________________________________________________________
Samuel P. Wilcock, PhD (Statistics, Virginia Tech)
Associate Professor of Mathematics and Statistics
Department of Information and Mathematical Sciences
Messiah College, Grantham, PA
Fall 2010 Sabbatical at:
Pennsylvania State University, Milton S. Hershey College of Medicine
Department of Public Health Sciences, Biostatistics Division
-------------------------------------------------------------------
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
|