name: Bug report about: Create a report to help us improve title: '' labels: bug assignees: ''
Please replace the descriptions below with your content that relates to that topic.
Some model classes have their emmeans support in another package -- e.g., the one that defines the model class itself. If so, is the bug really in that package, rather than in emmeans?
Often there are useful annotation that you'll miss if you post-process your code. Seeing the actual results may even explain what's happening!
# --- Actual results (YES):
emmeans(mod, ~ Sex)
## Sex emmean SE df asymp.LCL asymp.UCL
## F -1.432 0.582 Inf -2.572 -0.291
## M 0.392 0.492 Inf -0.573 1.356
##
## Results are averaged over the levels of: Treatment
## Results are given on the logit (not the response) scale.
## Confidence level used: 0.95
# --- Filtered results (NO):
emmeans(mod, ~ Sex) %>% as_tibble()
## # A tibble: 2 × 6
## Sex emmean SE df asymp.LCL asymp.UCL
## <fct> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 F -1.43 0.582 Inf -2.57 -0.291
## 2 M 0.392 0.492 Inf -0.573 1.36
A clear and concise description of what the bug is.
Show me code and output that reproduces the bug. Please use a small data set (built-in if possible) and simple variable names. And please, do not create different objects having the same name; to compare two or three different models or methods, give those objects different names so we can talk about them.
Show the actual output from whatever function is in question -- do not pipe it into some post-processing stuff. The actual output often shows some annotations that you don't see if you are trying to "tidy" it. Nothing would make me happier than to avoid all tidyverse code.
A clear and concise description of what you expected to happen.
Add any other context about the problem here.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.