Timeline for How to build scoring model (scorecard) from logistic regression?
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 14, 2017 at 22:11 | history | edited | mdewey |
Scores tag removed as deprecated
|
|
| Mar 21, 2016 at 13:29 | vote | accept | vonjd | ||
| Mar 21, 2016 at 13:25 | answer | added | vonjd | timeline score: 2 | |
| Oct 6, 2015 at 9:40 | comment | added | vonjd | @Scortchi: Yeah, silly mistake, so it is $log(.5/(1-.5)) = log(1) = 0$ | |
| Oct 6, 2015 at 9:30 | comment | added | Scortchi♦ | No - use the logit function, whose inverse is in your code above. The logit of 0.5 is 0. | |
| Oct 6, 2015 at 9:25 | comment | added | vonjd | @Scortchi: So basically if one wants to have a probability of $.5$ the threshold is $exp(.5)/(1-exp(.5)) = -2.54$ ? | |
| Oct 6, 2015 at 8:59 | comment | added | Scortchi♦ | (1) Express the threshold in log odds rather than probability. (2) You need to describe how that scorecard's arrived at. I suspect it's by fitting a different model to yours, in which the predictors are binned & coefficients estimated for each bin. | |
| Oct 6, 2015 at 8:00 | history | asked | vonjd | CC BY-SA 3.0 |