I'm trying the emmip_ggplot
with this example
n.emms <- emmeans(neuralgia.glm, ~ Treatment)
emmip_ggplot(n.emms, style = "factor")
Error in emms$LCL : $ operator not defined for this S4 class
emmip(neuralgia.glm, ~Treatment)
gives a traditional plot, without error or warning.
Thanks for stopping by.
CodePudding user response:
?emmip_ggplot
says the first argument to emmip_ggplot
should be
A ‘data.frame’ created by calling ‘emmip’ with ‘plotit = FALSE’. Certain variables and attributes are expected to exist in this data frame; see the section detailing the rendering functions.
Thus
m1 <- glm(vs~hp disp drat, family = binomial, mtcars)
em1 <- emmeans(m1, ~ disp * hp, at = list(hp = 50:300))
em2 <- emmip(em1, disp ~ hp, plotit = FALSE)
emmip_ggplot(em2)
This works (i.e. produces a plot) but I'm not sure it makes sense, as I threw the example together in a hurry.