4
$\begingroup$

Several texts (both online and published books) have been reviewed prior to asking this.

What diagnostics are accepted as best practise for a generalised linear mixed-effects model fitted in R using glmmPQL. I am modelling mortality incidence (count data) using repeated measures, longitudinal survival data. The response is either 0 (alive) or 1 (death). Therefore when plotting residuals, a random scatter is difficult to observe as the residuals cluster around the observed values of 0 or 1. How can I plot residuals that are easy to interpret when fitting a glmmPQL model? Is there a way to get one residual per unique subject as opposed to 1 residual per observation of a given subject?

What are the other goodness-of-fit measures/tests to apply to a glmmPQL model. E.g. it appears that AIC and BIC can not be obtained from a glmmPQL.

I would greatly appreciate any help, even if direction to certain texts.

Thanks

$\endgroup$

Your Answer

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

Browse other questions tagged or ask your own question.