Timeline for Does adding more variables into a multivariable regression change coefficients of existing variables?
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 13, 2013 at 16:30 | comment | added | gung - Reinstate Monica | That's an insightful point, @user603, but I think there might still be a place for multiple regression, in that if the other variables were meaningfully related to the response (albeit not the explanatory variable), they can reduce the residual variance leading to improved power & precision. | |
| Mar 13, 2013 at 16:24 | comment | added | user603 | If the answer were no, there would not be a need to do multivariable regression in the first place! (we could simply do many univariable ones) | |
| Mar 13, 2013 at 16:11 | history | edited | gung - Reinstate Monica | CC BY-SA 3.0 |
added tag; removed peripheral comments
|
| Mar 13, 2013 at 16:07 | answer | added | gung - Reinstate Monica | timeline score: 32 | |
| Mar 13, 2013 at 10:40 | answer | added | Glen_b | timeline score: 3 | |
| Mar 13, 2013 at 10:31 | answer | added | Peter Flom | timeline score: 3 | |
| Mar 13, 2013 at 9:27 | history | edited | Lukas Pleva | CC BY-SA 3.0 |
Clarified what I mean by "multivariable"
|
| Mar 13, 2013 at 9:25 | comment | added | ttnphns |
Please edit the question to be more precise. Do by multivariable you mean multiple independent variables ("multiple regression") or multiple dependent variables ("multivariate regression" or "MAN(C)OVA")?
|
|
| Mar 13, 2013 at 9:17 | history | asked | Lukas Pleva | CC BY-SA 3.0 |