Log in
Registertreatment effect [General Statistics]
Dear Shri,
treatment effect is not very important. Regulators do not regard a significant treatment effect as a problem. In a BE study you are using two different treatments so you know they are 'a little bit different'. It's the the magnitude of the (estimated) difference in combo with the associated uncertainty that matters. In other words, the CI.
To answer your question, I don't think I have a better explanation for a significant treatment effect than the fact that there are two different treatments involved. It takes some getting used to, esp. because significant trt effect and CI's that does not include 1.0 go hand-in-hand.
EM.
treatment effect is not very important. Regulators do not regard a significant treatment effect as a problem. In a BE study you are using two different treatments so you know they are 'a little bit different'. It's the the magnitude of the (estimated) difference in combo with the associated uncertainty that matters. In other words, the CI.
To answer your question, I don't think I have a better explanation for a significant treatment effect than the fact that there are two different treatments involved. It takes some getting used to, esp. because significant trt effect and CI's that does not include 1.0 go hand-in-hand.
EM.
Complete thread:
- treatment effect shri 2008-11-19 07:07
![[Mix]](https://static.bebac.at/img/mix.png "open in Mix view")
- treatment effectElMaestro 2008-11-19 09:38
Ing. Helmut Schütz