Timeline for Confidence intervals for emmeans estimates after multilevel binary logistic regression
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 9, 2018 at 15:55 | vote | accept | MGy | ||
| Oct 4, 2018 at 21:52 | answer | added | Russ Lenth | timeline score: 3 | |
| Oct 4, 2018 at 13:04 | comment | added | MGy | I see, I ran it wrong, my bad, thanks so much. Now I see the effect of A at each level of B - is there, however, a way to look at pairwise comparisons of the levels of B (i.e., is the effect of A different at level 1 of B compared to level 2?). Similarly to the three-way interaction question linked above. | |
| Oct 4, 2018 at 12:18 | comment | added | Russ Lenth | Also look at the row labels in your output. Just because you have the number of results you expected doesn’t mean they are the right results, and in this case you have a set of 6 comparisons of comparisons of cell means. | |
| Oct 4, 2018 at 12:12 | comment | added | Russ Lenth |
As constructed, emms has B as a by variable. If you don’t mess with it, pairs(emms) will produce separate comparisons of A at each B
|
|
| Oct 4, 2018 at 8:48 | comment | added | MGy | To put it in different terms: I assumed that each line here in the output I'm reporting corresponds to the A x B interaction, where the levels of B are restricted to two levels at a time. | |
| Oct 4, 2018 at 8:44 | comment | added | MGy |
Thanks! I did try that first but that gives me a list of (8*7)/2=28 comparisons while what I'm interested in is how the difference between the two levels of A differs between groups (6 comparisons, like above). (Similarly to what was going on here, but with a less complex interaction: stats.stackexchange.com/questions/355611/…)
|
|
| Oct 4, 2018 at 0:09 | comment | added | Russ Lenth |
Two things: 1. I think you want regular pairwise comparisons, not interaction contrasts. Skip that con step and do pairs(emm) directly. 2. Add type = “response”) to the emmeans call and the results will be back-transformed. OK, also 3. Look at the vignettes that come with emmeans for suggestions and examples.
|
|
| Oct 3, 2018 at 9:04 | history | asked | MGy | CC BY-SA 4.0 |