Hello,
We have a dataset which has both right- and interval-censored data. We are trying to fit a Weibull survival model with 2, 2-level covariates. We have struggled to make a model that will run. We have one that will run, but it requires indexing lambda (which doesn’t make sense in our case) and an intercept in the linear predictor (which also doesn’t make sense in our case). Failure to index lambda leads to the error ‘multiple definitions of lambda’. Failure to include the intercept leads to the error ‘Forward 8’. We also should note that we don’t have failure times for any of our individuals, they are all interval or right censored. This results in a t.obs vector of NAs. We were wondering if anyone has worked on a similar problem or if anyone might have insight into why we get the error messages. The 1st part is the right censored portion, the 2nd part is for the interval censored data. Here is the model:
model {
for(i in 1:397) {
tobs[i] ~ dweib(power,lambda[i])I(lower[i],)
lambda[i] <- exp(beta0 + beta1*island[i] + beta2*sex[i])
}
for(i in 398:n) {
tobs[i] ~ dweib(power,lambda[i])I(lower[i],upper[i])
lambda[i] <- exp(beta0 +beta1*island[i]+ beta2*sex[i])
}
power~dunif(0,10)
beta0 ~dnorm(0.0, 0.0001)
beta1~dnorm(0.0, 0.0001)
beta2~dnorm(0.0, 0.0001)
}
Thanks!
-------------------------------------------------------------------
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
|