Type III kuddel muddel [🇷 for BE/BA]
Dear Detlew & all,
Yes. An excerpt of the manual here and an example there. There is no guarantee that Phoenix/WinNonlin and SAS will be that close in all cases.
Duno. We explored package

I would rather say “[…] by which software and/or coding is their secret”. I never gave anything but the PE and CI in the main text of my reports (the complete evaluation only in the appendix). Although some assessors or inspectors routinely recalculate studies (in SAS or in the semi-secret WinBE?) I never received a question. Maybe they compared only the CI, which – as you said – is the only relevant part.
When it comes to the type III stuff I gather that it will be practically impossible (e.g., Phoenix/WinNonlin) or difficult (R?) to exactly reproduce SAS’ results. AFAIK only SPSS uses the same algo as SAS.
❝ WinNonlin/Phoenix uses a different form of F-Tests (not based on Type III sos) AFAIK.
Yes. An excerpt of the manual here and an example there. There is no guarantee that Phoenix/WinNonlin and SAS will be that close in all cases.
❝ So what can we suggest to Yung-jin w.r.t. the ANOVA?
❝ SAS way, Phoenix way, R's drop1()
(which doesn't work for sequence) or what else?
Duno. We explored package
lsmeans
in this lengthy thread without a final conclusion. For the R-community’s “dogma” see Venables’ paper* (section 5).❝ […] the primary concern, the 90% CI as bioequivalence measure doesn't depend in any way from such considerations. Thank goodness!

❝ But regulators like to see some sort of effect tests in the ANOVA. Which one is their secret
I would rather say “[…] by which software and/or coding is their secret”. I never gave anything but the PE and CI in the main text of my reports (the complete evaluation only in the appendix). Although some assessors or inspectors routinely recalculate studies (in SAS or in the semi-secret WinBE?) I never received a question. Maybe they compared only the CI, which – as you said – is the only relevant part.
When it comes to the type III stuff I gather that it will be practically impossible (e.g., Phoenix/WinNonlin) or difficult (R?) to exactly reproduce SAS’ results. AFAIK only SPSS uses the same algo as SAS.
- Venables WN. Exegeses on Linear Models. S-PLUS User’s Conference Washington, DC, 8–9th October, 1998.
free resouce.
PS: Kuddelmuddel ~ hash, jumble, mess…
—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png)
Helmut Schütz
![[image]](https://static.bebac.at/img/CC by.png)
The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png)
Helmut Schütz
![[image]](https://static.bebac.at/img/CC by.png)
The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Complete thread:
- R code for lm.mod does not make sense dmfisher 2015-06-09 03:55 [🇷 for BE/BA]
- R code for lm.mod does not make sense yjlee168 2015-06-09 17:57
- R code for lm.mod does not make sense ElMaestro 2015-06-09 21:07
- R code for lm.mod does not make sense yjlee168 2015-06-10 11:34
- R code for lm.mod does not make sense ElMaestro 2015-06-10 14:22
- R code for lm.mod does not make sense yjlee168 2015-06-11 09:44
- Reference datasets Helmut 2015-06-11 11:50
- Reference datasets ElMaestro 2015-06-11 12:01
- Reference datasets yjlee168 2015-06-11 22:16
- Type III kuddel muddel d_labes 2015-06-12 09:04
- Type III kuddel muddelHelmut 2015-06-12 11:27
- ANOVA F-test results and regulators d_labes 2015-06-12 15:23
- ANOVA F-test results and regulators ElMaestro 2015-06-12 15:29
- ANOVA F-test results and regulators d_labes 2015-06-12 15:44
- ANOVA F-test results and regulators ElMaestro 2015-06-12 15:52
- ANOVA F-test results and regulators d_labes 2015-06-12 15:44
- ANOVA F-test results and regulators ElMaestro 2015-06-12 15:29
- ANOVA F-test results and regulators d_labes 2015-06-12 15:23
- Type III again ElMaestro 2015-06-12 12:18
- SAS OT d_labes 2015-06-12 15:32
- Type III kuddel muddelHelmut 2015-06-12 11:27
- Reference datasets yjlee168 2015-06-11 19:56
- Test hypothesis of using Type I/III MS... yjlee168 2015-06-12 09:01
- Reference datasets ElMaestro 2015-06-11 12:01
- Reference datasets Helmut 2015-06-11 11:50
- R code for lm.mod does not make sense yjlee168 2015-06-11 09:44
- R code for lm.mod does not make sense ElMaestro 2015-06-10 14:22
- R code for lm.mod does not make sense yjlee168 2015-06-10 11:34
- R code for lm.mod does not make sense dmfisher 2015-06-10 01:38
- R code for lm.mod does not make sense ElMaestro 2015-06-09 21:07
- R code for lm.mod does not make sense yjlee168 2015-06-09 17:57