Bioequivalence and Bioavailability Forum • Restaurant solution

Restaurant solution [🇷 for BE/BA]

posted by mittyri – Russia, 2017-08-30 10:11 (3217 d 04:41 ago) – Posting: # 17754
Views: 10,028

Hi ElMaestro,

❝ When we look at treatment effect differences it does not matter how we define the effects by contrast coding. I don't absolutely need an LSMean; I can do with two model effects calcuated in any valid way as long as I can extract their difference.

Homecook is good, but sometimes you can go to restaurant :-D

library("lsmeans")

confint(pairs(lsmeans(M, "Trt"), reverse =TRUE), level=1-alpha*2)

I like this package, there is even support for nested structures in latest version.

—
Kind regards,
Mittyri

Complete thread:

confint() for difference of effect levels ElMaestro 2017-08-29 10:20
- confint() for difference of effect levels d_labes 2017-08-29 12:23
  - confint() for difference of effect levels ElMaestro 2017-08-29 14:45
    - Homecooked solution? ElMaestro 2017-08-29 23:18
      - Restaurant solutionmittyri 2017-08-30 08:11
        
        Great ElMaestro 2017-08-30 09:27
    - All-at-once or Two-at-a-time d_labes 2017-08-30 19:55