Log in
RegisterOn random effects and bogus statements [🇷 for BE/BA]
Hi Lizhao,
Actually, you will see that FDA own SAS code for analysis of 222BE-studies involves PROC GLM, and this will always fit all effects as fixed. Hence lm in R. This despite the fact that Chow&Liu mentions the subject effect as random. It turns out that when you run the analysis on completers (completers only!) then PROC GLM/lm or a mixed effect model will achieve exactly the same. The beauty of PROC GLM/lm is that you get a well-defined anova along with it if you want. A well-defined anova doesn't exist for mixed models (but anovas of sorts can still be constructed).
You will also see that in FDA's code for 222BE which is based on PROC GLM there is a
Both can be argued to be correct, but since mass hysteria and brainlessness have trumped common sense in recent years everyone and his cousin just seem to want to reproduce PROC GLM's output without any questions asked.
I think you can plot those curves in any way you want? The BE decision is taken on basis of the CI's.
If you plot Conc versus time and average across subjects then you would often choose to use between-subject variances for error bars.
❝ Thank you very much for your help. I do have a question about using lm() instead of lme() function in R. Based on my understanding, subject effect should be considered to be random effect
? If I use lm(), all effects are treated as fixed effects. You suggest me to use lm, is it based on FDA or EMA guidance?
Actually, you will see that FDA own SAS code for analysis of 222BE-studies involves PROC GLM, and this will always fit all effects as fixed. Hence lm in R. This despite the fact that Chow&Liu mentions the subject effect as random. It turns out that when you run the analysis on completers (completers only!) then PROC GLM/lm or a mixed effect model will achieve exactly the same. The beauty of PROC GLM/lm is that you get a well-defined anova along with it if you want. A well-defined anova doesn't exist for mixed models (but anovas of sorts can still be constructed).
You will also see that in FDA's code for 222BE which is based on PROC GLM there is a
random statement pertaining to subject. One should think this means we are now asking PROC GLM to add a random effect (and thus to analyse as a mixed model), perhaps. It doesnt, though. PROC GLM with the random statement for subject still treats subject as a fixed effect. The bogus statement achieves another goal and compares sequence against the subject MS, and for that there is no direct equivalent in R, and this is why will see that there is a difference in the ANOVAs generated from PROC GLM and R's drop1.Both can be argued to be correct, but since mass hysteria and brainlessness have trumped common sense in recent years everyone and his cousin just seem to want to reproduce PROC GLM's output without any questions asked.
❝ Another question would be related to plot mean curves of Test and Reference product. If I want to plot a mean plot (mean and error bars) of a crossover biequivalence study, should I use within-subject confidence intervals or between-subject confidence intervals? They are apparently quite different.
I think you can plot those curves in any way you want? The BE decision is taken on basis of the CI's.
If you plot Conc versus time and average across subjects then you would often choose to use between-subject variances for error bars.
—
Pass or fail!
ElMaestro
Pass or fail!
ElMaestro
Complete thread:
- R code for analyzing classical 2X2 crossover designed bioequivalence data lizhao 2016-01-22 00:13
![[Mix]](https://static.bebac.at/img/mix.png "open in Mix view")
- R code for analyzing classical 2X2 crossover designed bioequivalence data ElMaestro 2016-01-22 00:59
- R code for analyzing classical 2X2 crossover designed bioequivalence data lizhao 2016-01-22 01:26
- On random effects and bogus statementsElMaestro 2016-01-22 12:13
- FDA 'own' SAS code for 2x2 d_labes 2016-01-27 09:57
- FDA 'own' SAS code for 2x2 nobody 2016-01-27 10:09
- OT: PM to ElMaestro Helmut 2016-01-27 13:39
- On coffee and such... ElMaestro 2016-01-27 13:47
- FDA 'own' SAS code for 2x2 nobody 2016-01-27 10:09
- Geometric means ± SD Helmut 2016-01-27 13:51
- Geometric means ± SD nobody 2016-01-27 15:20
- Money makes the world go ’round Helmut 2016-01-27 16:11
- Money makes the world go ’round nobody 2016-01-27 16:31
- Fixed or random effect kumarnaidu 2016-11-04 14:05
- PROC GLM fixes Subject mittyri 2016-11-04 23:00
- PROC GLM fixes Subject kumarnaidu 2016-11-05 05:22
- PROC GLM fixes Subject mittyri 2016-11-05 10:13
- PROC GLM fixes Subject kumarnaidu 2016-11-07 06:24
- PROC GLM fixes Subject mittyri 2016-11-07 11:57
- PROC GLM fixes Subject kumarnaidu 2016-11-07 12:42
- PROC GLM fixes Subject mittyri 2016-11-07 11:57
- PROC GLM fixes Subject kumarnaidu 2016-11-07 06:24
- PROC GLM fixes Subject mittyri 2016-11-05 10:13
- PROC GLM fixes Subject kumarnaidu 2016-11-05 05:22
- PROC GLM fixes Subject mittyri 2016-11-04 23:00
- Fixed or random effect kumarnaidu 2016-11-04 14:05
- Money makes the world go ’round nobody 2016-01-27 16:31
- Money makes the world go ’round Helmut 2016-01-27 16:11
- Geometric means ± SD Ben 2016-11-08 21:20
- Misunderstanding Helmut 2016-11-09 15:29
- Misunderstanding Ben 2016-11-14 19:40
- RTFM Helmut 2016-11-14 21:50
- Misunderstanding Ben 2016-11-14 19:40
- Misunderstanding Helmut 2016-11-09 15:29
- Geometric means ± SD nobody 2016-01-27 15:20
- FDA 'own' SAS code for 2x2 d_labes 2016-01-27 09:57
- On random effects and bogus statementsElMaestro 2016-01-22 12:13
- R code for analyzing classical 2X2 crossover designed bioequivalence data lizhao 2016-01-22 01:26
- R code for analyzing classical 2X2 crossover designed bioequivalence data ElMaestro 2016-01-22 00:59
Ing. Helmut Schütz