Timeline for where to specify covariates in a linear mixed effect model
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 26, 2019 at 14:35 | history | edited | Tony K | CC BY-SA 4.0 |
restructured for clarity (thanks Ous)
|
| Jun 26, 2019 at 14:17 | comment | added | Tony K | Whoops, thanks for catching that. I actually tend to use that explicit redundancy just so I don't get lost when specifying complex models. | |
| Jun 26, 2019 at 7:20 | comment | added | Ous |
Actually (biomass|site) expands to (1+biomass|site), so you already have both slope and intercept there. Therefore, (1|site) + (biomass|site) is redundant. If you want to omit the random intercept (which is generally not a good idea), you need to force it: (0+biomass|ste).
|
|
| Jun 25, 2019 at 14:17 | history | answered | Tony K | CC BY-SA 4.0 |