Timeline for Model selection in mixed-effects model with collinearity trouble
Current License: CC BY-SA 3.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 6, 2015 at 22:18 | vote | accept | Jan | ||
| Aug 6, 2015 at 13:08 | comment | added | Jan | Thank you for the quick answer! I will try the leaps package. Indeed the purpose is to determine which/if variables matter, which is why I have a hard time solely relying on the AIC, since in some cases it means excluding variables with a significant F-statistic (even though mostly with coefficients not different from zero, when looking at the summary). Unfortunately, a balanced design is not possible. | |
| Aug 6, 2015 at 12:14 | history | answered | Placidia | CC BY-SA 3.0 |