Timeline for Regression metrics when underestimation is worse than overestimation
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 20, 2023 at 16:01 | answer | added | Dave | timeline score: 2 | |
| Jul 13, 2020 at 11:00 | comment | added | Nick Cox | How to do any of this with your preferred software is a different question and in any event I couldn't offer advice on software I've never used. | |
| Jul 13, 2020 at 10:59 | comment | added | Nick Cox | @Dave That's changing the question, but the answer might be helpful. | |
| Jul 13, 2020 at 10:00 | comment | added | Slajni | How can I use it with library models like for example sklearns random forest regressor? | |
| Jul 13, 2020 at 9:56 | comment | added | Dave | @NickCox What would you say to quantile regression at, say, quantile $0.25?$ This would make the model prefer to miss low than to miss high. | |
| Jul 13, 2020 at 9:52 | comment | added | Nick Cox | You can write down a loss function and then write code to minimise it. In principle that is the entire solution. Or you might find that working with root or log of time (the latter only if all times are positive) gives you an adequate approximation. | |
| Jul 13, 2020 at 9:43 | history | asked | Slajni | CC BY-SA 4.0 |