Log in
RegisterLinear model on steroids [Software]
Hi dlabes,
In matrix notation, the normal linear model is written y = Xb + e, and the normal linear mixed model is y = Xb + Zg + e,
i.e. the mixed one is just the linear one plus the Zg-term (model matrix for the random effects and the corresponding random effects vector). "On steroids" is a phrase used to indicate that something has been extended/inflated/improved/enlarged/souped-up etc.
Finally, your explanation about the bogus term is very fine - I did not know that it results in an anova table with the correct F/P-value for the sequence effect. But I think it misses my point slightly. To me, manuals/documentation is where I look and read when I am faced with a problem. How do I etc and why. Let's say you are in a situation where you need to analyse a 2-treatment, 4-period BE study. OK, so you need a mixed model. But should you go for PROC MIXED or PROC GLM in combo with the bogus statement? Does the documentation reffed above help chosing here? I think it doesn't; in fact I think it adds more confusion than it helps. One of the old jokes about the Delphi programming language was that you needed to be an expert Delphi programmer in order to understand the Delphi manual. You see a parallel?
Best regards
EM.
PS: I would use MIXED.
❝ BTW: Could you explain your "Linear model on Steroids" a bit more in detail? I couldn't get the the joke.
In matrix notation, the normal linear model is written y = Xb + e, and the normal linear mixed model is y = Xb + Zg + e,
i.e. the mixed one is just the linear one plus the Zg-term (model matrix for the random effects and the corresponding random effects vector). "On steroids" is a phrase used to indicate that something has been extended/inflated/improved/enlarged/souped-up etc.
Finally, your explanation about the bogus term is very fine - I did not know that it results in an anova table with the correct F/P-value for the sequence effect. But I think it misses my point slightly. To me, manuals/documentation is where I look and read when I am faced with a problem. How do I etc and why. Let's say you are in a situation where you need to analyse a 2-treatment, 4-period BE study. OK, so you need a mixed model. But should you go for PROC MIXED or PROC GLM in combo with the bogus statement? Does the documentation reffed above help chosing here? I think it doesn't; in fact I think it adds more confusion than it helps. One of the old jokes about the Delphi programming language was that you needed to be an expert Delphi programmer in order to understand the Delphi manual. You see a parallel?
Best regards
EM.
PS: I would use MIXED.
Complete thread:
- SAS vs. WinNonlin: different sequence effect results Eva 2008-05-06 14:04
![[Mix]](https://static.bebac.at/img/mix.png "open in Mix view")
- SAS vs. WinNonlin: different sequence effect results Ohlbe 2008-05-06 15:56
- imbalanced design? Helmut 2008-05-06 16:13
- Sample data & results Eva 2008-05-06 17:42
- Error factor Ohlbe 2008-05-06 19:25
- Error tests between/within Helmut 2008-05-06 21:33
- Error tests between/within Helmut 2008-05-07 18:18
- The power to know d_labes 2008-05-08 11:16
- The power to know Helmut 2008-05-08 17:18
- The power to know d_labes 2008-05-09 09:35
- The power to know Nirali 2008-05-09 11:00
- The power to know d_labes 2008-05-16 08:54
- The power to know Nirali 2008-05-09 11:00
- The power to know d_labes 2008-05-09 09:35
- The power to know kevan 2009-05-25 15:46
- Bogus statement for 2,2,2-BE ElMaestro 2009-05-25 22:25
- Bogus? What? d_labes 2009-05-27 08:57
- Linear model on steroidsElMaestro 2009-05-28 19:12
- Bogus? What? d_labes 2009-05-27 08:57
- Fixed nowadays what? d_labes 2009-05-27 09:03
- Bogus statement for 2,2,2-BE ElMaestro 2009-05-25 22:25
- The power to know Helmut 2008-05-08 17:18
- Kinetica 5.0 bug Helmut 2008-12-31 16:42
- Error tests between/within Helmut 2008-05-06 21:33
- Error factor Ohlbe 2008-05-06 19:25
- Sample data & results Eva 2008-05-06 17:42
Ing. Helmut Schütz