I am using the 'emmeans' package in R to compute estimated marginal means for my (liner mixed-effects) model. However, I am enountering a warning message related to the number of observations exceeding 3000. Here is the specific code and the warning message I am receiving:
emmeans_results <- emmeans(lmer_model, ~ intervention + group)
The Warning Message is:
Note: D.f. calculations have been disabled because the number of observations exceeds 3000. To enable adjustments, add the argument 'pbkrtest.limit = 161345' (or larger) [or, globally, 'set emm_options(pbkrtest.limit = 161345)' or larger]; but be warned that this may result in large computation time and memory use. Note: D.f. calculations have been disabled because the number of observations exceeds 3000. To enable adjustments, add the argument 'lmerTest.limit = 161345' (or larger) [or, globally, 'set emm_options(lmerTest.limit = 161345)' or larger]; but be warned that this may result in large computation time and memory use.
How can I handle this issue without running into significant computation time and memory use (setting lmerTest.limit = 161345 causes the R to crash on my computer). Is there a recommended approach for dealing with this in 'emmeans'?
options = list(lmer.df = "asymptotic")should give a z-test instead of a t-test, but since you have so much data that should be okay. Also see stats.stackexchange.com/questions/559059/…