1
$\begingroup$

I am still attempting to use jointLCMM to model trajectories of a risk variable while controlling for data missing not at random due to survival events.

I am trying to control for multiple events resulting in sequence truncation. My code for the survival component is

Surv(time_event, status)~covariate, hazard="Weibull"

I keep getting an error message

Error in rep(c(sqrt(sum(devt == i)/sum(tsurv[devt == i])), 1), ifelse(risqcom == : invalid 'times' argument

When I was running it without competing events, using

Surv(entrytime, exittime, event_flag)

it worked fine. I tried a bunch of potential fixes but none of them worked. Have any of you got ideas of what this error message means/how to fix it? Thanks!!

$\endgroup$

1 Answer 1

0
$\begingroup$

In case anyone in the future has this problem- the issue ended up being that I had four competing risk events (censoring, outcome A, outcome B, outcome C). After I collapsed outcomes B and C the model was able to run.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.