0

How do I perform a post hoc test for a random effect beta distribution?

To build the mixed model with beta distribution I used the library gamlss (I found no other way to do this in R). In this model there is a factor with three levels. Suppose level1, level2 and level3. The summary shows the comparison between level1 x level2 and level1 x level3, since level1 is the baseline.

library(gamlss) mymodel <- gamlss(response~ph+dose, family = BE, random=~1|id, data = mydata) summary(mymodel)

It shows the comparison between level1 x level2 and level1 x level3

For all three levels, the summary shows the comparison between level1 x level2 and level1 x level3, as level1 is the baseline.

I would like to test if there is difference between level2 x level3. How can I do this? Maybe there could be another library for this. Can anyone please help me?

Omar
  • 19
  • 3

1 Answers1

-1

I would suggest you to have a look at the package "emmeans". 

    library("emmeans")
    Post_Hoc <- emmeans (model, specs = pairwise ~ Var, type = "response")
    summary(Post_Hoc)

Good luck

Tibo

lczapski
  • 4,026
  • 3
  • 16
  • 32
Tibo
  • 1
  • 1