Timeline for Computation and Interpretation of Odds Ratio with continuous variables with interaction, in a binary logistic regression model
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 18, 2018 at 2:04 | comment | added | Heteroskedastic Jim | @baxx there's nothing stopping you from interpreting the exponentiated coefficient but it's only true when B = 0. And as in my example, that can be grossly irrelevant. | |
| Nov 18, 2018 at 1:47 | comment | added | Heteroskedastic Jim | @baxx something like that. It depends on the value of B. You effectively tie them together by setting up an interaction. | |
| Nov 18, 2018 at 1:38 | comment | added | baxx | From this then, it's not possible to only give the odds ratio of $A$ in this context? By which I mean, reporting $\exp(0.756)$ is incorrect because of the interaction ( I can't report this as being adjusted for B and AxB ). And in the case of $\exp(\beta_1 + \beta_3 \times B )$ it's not an odds ratio only for $A$, because it contains B. Does that make sense? Thanks | |
| Nov 17, 2018 at 22:45 | history | edited | Heteroskedastic Jim | CC BY-SA 4.0 |
added 67 characters in body
|
| Nov 17, 2018 at 22:38 | history | answered | Heteroskedastic Jim | CC BY-SA 4.0 |