bear v1.0.0 - a data analytical tool for ABE in R [🇷 for BE/BA]
Dear Yung-jin,
I don't think the software should state it uses GLM if it doesn't. But that's of course only a personal view and I mean no offense at all.
Regarding proc mixed and proc GLM in SAS my impression is* that for balanced data they achieve the same thing, but proc mixed is more computationally intensive. Therefore, in the old days when computers were slow GLM was preferred. Nowadays, when computational power is not an issue it makes little difference.
For data without balance, however, proc mixed is used and proc GLM may be unsafe. All in all, one can say it is always kind of safe to use proc mixed.
Thus, I'd suggest you to use a mixed model the following way:
"lmeYungjin <- LnAUC0INF ~ seq + prd + drug, random=~1|subj, method="REML")
From the lmeYungjin fit you can extract the correct sigma (which is correct whether or not you have balance) and the treatment difference and use this to construct the 90% CI.
Next, you can do a glm as follows:
"glmYungjin <- glm(LnAUC0INF ~ seq + prd + drug + subj)"
followed by "drop1(glmYungjin, test="F") to get a glm anova with type III SS.
Last you just need to update the anova with the correct error term for the sequence effect (between subj error).
Result: Anova and 90% CI done the way SASoholics like and it is resistant to imbalance....
Best regards
EM
*: When I say "my impression is" then it of course means I could be completely wrong and I'd be happy to stand corrected accordingly.
I don't think the software should state it uses GLM if it doesn't. But that's of course only a personal view and I mean no offense at all.
Regarding proc mixed and proc GLM in SAS my impression is* that for balanced data they achieve the same thing, but proc mixed is more computationally intensive. Therefore, in the old days when computers were slow GLM was preferred. Nowadays, when computational power is not an issue it makes little difference.
For data without balance, however, proc mixed is used and proc GLM may be unsafe. All in all, one can say it is always kind of safe to use proc mixed.
Thus, I'd suggest you to use a mixed model the following way:
"lmeYungjin <- LnAUC0INF ~ seq + prd + drug, random=~1|subj, method="REML")
From the lmeYungjin fit you can extract the correct sigma (which is correct whether or not you have balance) and the treatment difference and use this to construct the 90% CI.
Next, you can do a glm as follows:
"glmYungjin <- glm(LnAUC0INF ~ seq + prd + drug + subj)"
followed by "drop1(glmYungjin, test="F") to get a glm anova with type III SS.
Last you just need to update the anova with the correct error term for the sequence effect (between subj error).
Result: Anova and 90% CI done the way SASoholics like and it is resistant to imbalance....
Best regards
EM
*: When I say "my impression is" then it of course means I could be completely wrong and I'd be happy to stand corrected accordingly.
Thread locked
Complete thread:
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-12 20:53 [🇷 for BE/BA]
- bear v1.0.0 for R - first impressions Helmut 2008-07-14 04:12
- bear v1.0.0 for R - first impressions yjlee168 2008-07-14 10:26
- bear v1.0.0 for R - first impressions Helmut 2008-07-14 14:02
- bear v1.0.0 for R - first impressions yjlee168 2008-07-14 18:12
- bear v1.0.0 for R... Helmut 2008-07-14 18:56
- bear v1.0.0 for R... yjlee168 2008-07-14 19:30
- bear v1.0.0 for R... Helmut 2008-07-14 20:35
- bear v1.0.0 for R... yjlee168 2008-07-14 19:30
- bear v1.0.0 for R... Helmut 2008-07-14 18:56
- bear v1.0.0 for R - first impressions yjlee168 2008-07-15 09:44
- bear v1.0.0 for R - first impressions yjlee168 2008-07-14 18:12
- bear v1.0.0 for R - first impressions Helmut 2008-07-14 14:02
- bear v1.0.0 for R - first impressions yjlee168 2008-07-14 10:26
- bear v1.0.0 - a data analytical tool for ABE in R martin 2008-07-14 12:18
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-14 19:02
- bear v1.0.0 - a data analytical tool for ABE in R Aceto81 2008-07-15 10:07
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-16 07:22
- bear v1.0.0 - a data analytical tool for ABE in R Aceto81 2008-07-16 09:47
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-16 21:32
- bear v1.0.0 - a data analytical tool for ABE in R Aceto81 2008-07-16 09:47
- lambda_z estimation yjlee168 2008-09-23 12:13
- lambda_z estimation d_labes 2008-09-23 14:41
- lambda_z estimation yjlee168 2008-09-24 22:41
- lambda_z estimation Aceto81 2008-09-25 10:56
- lambda_z estimation yjlee168 2008-09-25 21:00
- lambda_z estimation yjlee168 2008-09-26 08:03
- lambda_z estimation Aceto81 2008-09-26 10:25
- lambda_z estimation yjlee168 2008-09-28 00:08
- lambda_z estimation yjlee168 2008-09-29 13:32
- WinNonlin 5.2.1 vs. 6 beta Helmut 2008-09-29 15:54
- WinNonlin 5.2.1 vs. 6 beta yjlee168 2008-09-29 18:45
- WinNonlin 5.2.1 vs. 6 beta --> new finding yjlee168 2008-09-30 08:10
- Example 4 in SASophylistic d_labes 2008-09-30 09:43
- Example 4 in SASophylistic yjlee168 2008-09-30 12:23
- Example 4 in SASophylistic d_labes 2008-09-30 09:43
- WinNonlin 5.2.1 vs. 6 beta Helmut 2008-09-29 15:54
- lambda_z estimation Aceto81 2008-09-26 10:25
- TTT method for lambda_z estimation yjlee168 2008-09-30 12:34
- TTT method for lambda_z estimation d_labes 2008-09-30 14:48
- TTT method for lambda_z estimation yjlee168 2008-09-30 20:28
- TTT method plus best fit combined d_labes 2008-10-01 08:43
- AIC or ARS as the best fit criterion? yjlee168 2008-10-02 12:40
- AIC or ARS as the best fit criterion? d_labes 2008-10-02 13:59
- AIC or ARS as the best fit criterion? yjlee168 2008-10-02 12:40
- TTT method plus best fit combined d_labes 2008-10-01 08:43
- TTT method for lambda_z estimation yjlee168 2008-09-30 20:28
- TTT method for lambda_z estimation Aceto81 2008-09-30 15:11
- TTT method for lambda_z estimation yjlee168 2008-09-30 19:57
- TTT method for lambda_z estimation Aceto81 2008-10-01 14:18
- TTT method for lambda_z estimation yjlee168 2008-10-02 12:29
- TTT method for lambda_z estimation Aceto81 2008-10-03 15:33
- TTT method for lambda_z estimation yjlee168 2008-10-03 21:22
- TTT method for lambda_z estimation Aceto81 2008-10-03 15:33
- TTT method for lambda_z estimation yjlee168 2008-10-02 12:29
- TTT method for lambda_z estimation Aceto81 2008-10-01 14:18
- TTT method for lambda_z estimation yjlee168 2008-09-30 19:57
- TTT method for lambda_z estimation d_labes 2008-09-30 14:48
- lambda_z estimation d_labes 2008-09-23 14:41
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-16 07:22
- bear v1.0.0 - a data analytical tool for ABE in R Aceto81 2008-07-15 10:07
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-14 19:02
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-07-22 14:35
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-23 09:55
- bear v1.0.0 - a data analytical tool for ABE in RElMaestro 2008-07-24 10:04
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-25 20:38
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-07-28 08:42
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-25 20:38
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-09-23 16:10
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-09-24 22:00
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-09-25 09:03
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-09-25 13:52
- bear v1.0.0 - a data analytical tool for ABE in R Helmut 2008-09-25 14:39
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-09-25 14:55
- bear v1.0.0 - a data analytical tool for ABE in R Helmut 2008-09-25 15:33
- GLM in R and the power to know d_labes 2008-09-25 16:45
- GLM in R and the power to know ElMaestro 2008-09-25 19:23
- nesting in R? yjlee168 2008-09-25 20:49
- nesting in R? ElMaestro 2008-09-25 22:01
- lm in R Helmut 2008-09-26 00:23
- nesting in R? yjlee168 2008-09-25 20:49
- GLM in R and the power to know ElMaestro 2008-09-25 19:23
- GLM in R and the power to know d_labes 2008-09-25 16:45
- bear v1.0.0 - a data analytical tool for ABE in R Helmut 2008-09-25 15:33
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-09-25 14:55
- bear v1.0.0 - a data analytical tool for ABE in R Helmut 2008-09-25 14:39
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-09-25 13:52
- bear v1.0.0 - a data analytical tool for ABE in R ElMaestro 2008-09-25 09:03
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-09-24 22:00
- bear v1.0.0 - a data analytical tool for ABE in RElMaestro 2008-07-24 10:04
- Type III SS in balanced, crossover BE studies? yjlee168 2008-10-18 21:03
- Type III SS in balanced, crossover BE studies? ElMaestro 2008-10-21 13:09
- Type III SS in balanced, crossover BE studies? yjlee168 2008-10-21 13:19
- Only balanced, crossover BE studies? d_labes 2008-10-21 14:31
- Only balanced, crossover BE studies? yjlee168 2008-10-21 19:01
- Only balanced, crossover BE studies? ElMaestro 2008-10-24 11:26
- Thread locked Helmut 2008-10-24 11:58
- Only balanced, crossover BE studies? ElMaestro 2008-10-24 11:26
- Only balanced, crossover BE studies? yjlee168 2008-10-21 19:01
- Only balanced, crossover BE studies? d_labes 2008-10-21 14:31
- Type III SS in balanced, crossover BE studies? yjlee168 2008-10-21 13:19
- Type III SS in balanced, crossover BE studies? ElMaestro 2008-10-21 13:09
- bear v1.0.0 - a data analytical tool for ABE in R yjlee168 2008-07-23 09:55
- bear v1.0.0 for R - first impressions Helmut 2008-07-14 04:12