Hi all,
I've the following model.. The observed quantities follow a Poisson model.
The Poisson mean is function of consumer carac (indice : qtte[j,1]). and
purchase occasion variables (indice j)
*model;
{
for( i in 1 : Nind )
{
time[i] ~ dnorm(m.time,p.time)
ltime[i] ~ dnorm(m.ltime,p.ltime)
}
for( j in 1 : Nobs )
{
qtte[j,3] ~ dpois(lam[j])
lam[j] ~ dgamma(p.taux,m.taux[j])
log(m.taux[j]) <- cstte + last*qtte[j,4] +
time[qtte[j,1]]*qtte[j,2]/7 + ltime[qtte[j,1]]*log(qtte[j,2]) +
vis*ind[qtte[j,1],1] + irr*ind[qtte[j,1],2]
lik[j] <- qtte[j,3]*log(lam[j])-lam[j]-logfact(qtte[j,3])
}
llik <- sum( lik[])
}
The model is running quite fine and I have the estimates for each quantity..
I took a sub-sample of my data and the model is still putting a whole day to
be estimated. I need some help in order to generalize this model to my whole
data (this for several product categories).. Should a switch to C/C+? (I'm
at the novice level) Is WBDev of some help?
TIA
Naji Nassar
-------------------------------------------------------------------
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
|