Timeline for Logistic regression - Confidence interval for x axis
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 31, 2022 at 10:36 | vote | accept | MOOSE | ||
| Aug 30, 2022 at 7:21 | comment | added | MOOSE | Thanks for the answer. This also seems like a natural way to do it. Initially, I was hesitant to define it this way because in the solution for the upper and lower limit the term $\log\left(\frac{p}{1-p}\right)$ shows up which diverges as $p$ approaches either $1$ or $0$. It seems to cause difficulty if we're interested in e.g ED90 instead of ED50. Do you have a comment for this limit? I'm not trying to be picky on your answer or anything, just trying to understand whats going on. | |
| Aug 29, 2022 at 19:56 | comment | added | JimB | And depending on the data, one can get $-\infty$ and/or $+\infty$ for the confidence limits. | |
| Aug 29, 2022 at 19:55 | history | edited | JimB | CC BY-SA 4.0 |
Changed "they" to "the".
|
| Aug 29, 2022 at 15:42 | history | answered | JimB | CC BY-SA 4.0 |