How to add Kenward-Roger approximation in a LMM?

I am comparing a series of 17 different LMMs and I am getting the warning message "boundary (singular) fit: see help('isSingular')" that could be related to low sample size. I was told that I could add Kenward-Roger approximation in the models to account for low sample size. So I am trying to find out how to best do that. Anybody can help me?

Is it always a comparison between large and small models? If yes, am I still able to run it since I am comparing 17 models?

Here is just an example of one of the models I am running:
oc <- lmer(Cortisol ~ Month + Year + Local + Age + Status + ΣPFAS + (1|ID), data = model)

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.