Dear WinBugs users,
I am trying to run the next ordered probit model with WinBUGS. I
have taken references of Simon Jackman and his example
"Delegation". There are no problems to compile and to initialize the
model with initial values. But, when I update it this mistake occurs:
"linear predictor in probit regression too large". I don't know where
the problem is, in the structure of the model or in the initial values.
Any ideas greatly appreciated.
Thanks in Advance,
model{
for (i in 1:N){
estar.mu[i]<-beta[1]+beta[2]*x[i,1]+beta[3]*x[i,2];
estar[i]~dnorm(estar.mu[i], tau);
probit(Q[i,1])<- (-estar[i]);
probit(Q[i,2])<- gamma - estar[i];
p[i,1] <- Q[i,1];
p[i,2] <- Q[i,2] - Q[i,1];
p[i,3]<- 1-Q[i,2];
e[i] ~ dcat(p[i,]);
}
tau ~ dgamma(1,1);
beta[1:3] ~ dmnorm(b0[], B0[,]);
a~dnorm(1,1);
gamma <- exp(a);
}
list(b0=c(1,1,1),B0=structure(.Data=c(0.00001,0,0,0,0.00001,0,0,0,
0.00001),.Dim=c(3,3)),N=100)
list(beta=c(1,1,1),a=1,tau=1,estar=c(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1))
x[,1] x[,2] e[]
0 47 1
0 53 1
0 63 1
0 63 1
...
1 42 3
1 56 3
1 50 3
Miguel Ángel Negrín Hernández
Dpt. of Quantitative Methods.
Fac. CC. Economicas. Modulo D. Campus de Tafira.
University of Las Palmas de G.C.
35017 Las Palmas de G.C. Spain.
Email:[log in to unmask]
-------------------------------------------------------------------
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
|