Hello Sa,

You'll need to provide more information for anyone to help you. Are you working directly in WinBUGS or using a pass-through like R2WinBUGS? Could you elaborate on what specific error message is coming up in WinBUGS and post it here? Cheers.

thanks for your answer. I am working directly with it. when I generate inits, software output is "value of categorical Y[1,3] must be an integer". this is part of my model:

for (i in 1:n){

for (j in 1:p){

Y[i , j] ~ dcat ( prob [i , j , 1: M[j]])

.......

list(n=10, p=8)

M[ ] M[ ] M[ ] M[ ] M[ ] M[ ] M[ ] M[ ]

4 3 3 4 4 4 5 3

4 4 5 3 5 4 3 4

5 5 5 3 5 5 5 5

......

I solved my problem, thanks

Glad you figured it out. Was it just a code typo? If you think it would be helpful to other WinBUGers please consider posting your solution to the problem. Cheers,

J

Hello, Mina. I am facing the same problem. Could you please tell me how to solve the prblem?

Mina may you post your answer, I have the same problem,please help?

Just in case someone else comes across this, I had this same problem and the issue was with the initial values. Using the initial values R script provided by Kery and Schaub (https://www.amazon.com/Bayesian-Population-Analysis-using-WinBUGS/dp/0123870208), I got it to work fine.

Is it possible to post this initial values r script here, otherwise some of us we cant access that book as one has to pay.

I  would appreciate if do that.

Marc Kéry and Michael Schaub wrote a great book that I would recommend to anyone fitting models in a Bayesian framework. It is definitely worth the investment. They also have a companion website that provides all the R script (http://www.vogelwarte.ch/de/projekte/publikationen/bpa/). It is the "ms.init.z" function.

could you help me write the winbugs program to estimate standized mortality rate (SMR) after a hieachical logistic model regression