Timeline for Is it worthwhile to use LASSO for variable selection even if it is cumbersome?
Current License: CC BY-SA 4.0
17 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 4, 2023 at 21:53 | answer | added | CrossVal_Asker | timeline score: 0 | |
| Dec 25, 2022 at 15:00 | history | tweeted | twitter.com/StackStats/status/1607028405383401473 | ||
| Dec 25, 2022 at 14:57 | comment | added | dipetkov | There are many CV threads that might be of interest. For example: Causal Inference After Feature Selection and A more definitive discussion of variable selection. | |
| Dec 25, 2022 at 14:53 | comment | added | dipetkov | In comments the OP clarifies that they are interested in "understand(ing) real world relationships. (...) I think they are layered effects. Like x1 and x2 directly influence Y, but x1 itself is influenced by x4 and x7." The language of "direct influence" suggests that you really want to do is causal inference. If that's the case, feature selection is basically irrelevant and in fact you cannot build the causal graph from the data. Instead, you could use the prior domain knowledge to construct the causal graph and start from there. | |
| Dec 25, 2022 at 14:26 | comment | added | User1865345 | @CrossVal_Asker I have edited your title, if you don't mind. | |
| Dec 25, 2022 at 14:25 | history | edited | User1865345 | CC BY-SA 4.0 |
edited title
|
| Dec 25, 2022 at 12:05 | comment | added | CrossVal_Asker | ok thanks! and merry christmas! | |
| Dec 25, 2022 at 11:12 | comment | added | Christian Hennig | 250 is an OK number for 10 variables. 110 is maybe a bit on the low side, but probably still not low enough that I'd say you have to do any variable selection (see my answer). | |
| Dec 25, 2022 at 11:05 | comment | added | CrossVal_Asker | @christian My sample size (number of observations) is 110 and as more data is coming in, it will be 250. | |
| Dec 25, 2022 at 10:11 | answer | added | Christian Hennig | timeline score: 9 | |
| Dec 25, 2022 at 10:00 | comment | added | Christian Hennig | What is your sample size? | |
| Dec 25, 2022 at 10:00 | history | became hot network question | |||
| Dec 25, 2022 at 9:39 | answer | added | Sextus Empiricus | timeline score: 6 | |
| Dec 25, 2022 at 8:52 | answer | added | Sohil Sharma | timeline score: 3 | |
| Dec 25, 2022 at 3:26 | comment | added | John Madden | "do I absolutely have to use lasso?" no, and I'm sure we're all wondering where on earth you got this idea :) May be worth checking out this Wikipedia page which lists some variable selection methods (only some of which are lasso ;) en.wikipedia.org/wiki/Feature_selection) | |
| S Dec 24, 2022 at 23:37 | review | First questions | |||
| Dec 24, 2022 at 23:39 | |||||
| S Dec 24, 2022 at 23:37 | history | asked | CrossVal_Asker | CC BY-SA 4.0 |