Timeline for Is it possible to perform a regression where you have an unknown / unknowable feature variable?
Current License: CC BY-SA 4.0
15 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 20, 2021 at 13:55 | comment | added | user2974951 | @GraemeWalsh In other words... "assume a can opener". | |
| Sep 7, 2019 at 10:00 | comment | added | Graeme Walsh | @SomeRandomPhysicist See, for example, section 2 of this paper - Measuring Potential Output within a State-Space Framework by Maral Kichian (Bank of Canada). | |
| Aug 24, 2019 at 21:00 | history | tweeted | twitter.com/StackStats/status/1165368193097093127 | ||
| Aug 24, 2019 at 19:39 | answer | added | Bertrand | timeline score: 0 | |
| Aug 24, 2019 at 11:53 | comment | added | Graeme Walsh | Yes. An unobserved component model / state space model can be used to do this. A classic example is modeling potential output (unobserved or latent variable) in economics. Essentially, you assume how this state variable evolves over time and can estimate it using a Kalman filter. | |
| Aug 23, 2019 at 18:49 | history | became hot network question | |||
| Aug 23, 2019 at 14:20 | comment | added | Chris Haug | What about a state space model? | |
| Aug 23, 2019 at 12:19 | answer | added | CloseToC | timeline score: 3 | |
| Aug 23, 2019 at 11:30 | vote | accept | SomeRandomPhysicist | ||
| Aug 23, 2019 at 11:29 | answer | added | user2974951 | timeline score: 15 | |
| Aug 23, 2019 at 11:19 | comment | added | mkt | @user2974951 Why not turn that into an answer? I don't even think you would need to expand on that. | |
| Aug 23, 2019 at 11:15 | comment | added | SomeRandomPhysicist | Thanks for the answers, just wanted some confirmation that this was the case as I suspected. I guess one could still perform the regression on the other feature variables if the effect of $x_3$ was very weak relative to the other feature variables, and so could be neglected entirely, but in the case where it is a large contribution regression is impossible. | |
| Aug 23, 2019 at 10:58 | comment | added | Łukasz Deryło | If it was possible, world would be beautiful! Just imagine: no data collection! no data wrangling! no people sending you data as screenshot embeded in Word document... | |
| Aug 23, 2019 at 10:56 | comment | added | user2974951 | No, how would you know what is attributable to the feature and what is just random? | |
| Aug 23, 2019 at 10:48 | history | asked | SomeRandomPhysicist | CC BY-SA 4.0 |