Plot REimpact plots on the same chart

[jknowles]

This will allow more direct comparison of random effects for users:

d_eff$Grouping_Factor <- "d"
s_eff$Grouping_Factor <- "s"
 
library(tidyverse)
 
rbind(d_eff, s_eff) %>%
  ggplot(aes(x=Grouping_Factor, y = AvgFit, color = Grouping_Factor)) +
    geom_point() +
    theme_minimal() +
    facet_grid(.~case) +
    scale_y_continuous(breaks = 0:5, limits = c(0, 5)) +
    labs(title = "Impact of grouping terms (s and d)")