Timeline for Determining the Weight of Categorical Variable's Coefficient
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 11, 2021 at 8:53 | comment | added | Maarten Buis | @Joon I have edited my answer to clarify that to answer your question you need to find a way to compare apples and oranges. This is possible (they are both fruit), but in doing so you necessarily also loose something. My rule of thumb would be to assume that this question is not relevant, and require some really really really strong arguments to move away from that assumption. If you have that strong argument you can look at the sheafcoeficient, as I mentioned in the answer. | |
| Mar 11, 2021 at 8:43 | history | edited | Maarten Buis | CC BY-SA 4.0 |
added 1567 characters in body
|
| Mar 11, 2021 at 4:18 | comment | added | Joon | (Assuming that this is one of the cases where it is relevant) | |
| Mar 11, 2021 at 4:17 | comment | added | Joon | Thanks for the answer. If I consider another case, in which variable is a categorical variable like nationality, I may be wondering if a person's age has more weight on the outcome of classification or his/her nationality has more weight. In this case I may wonder if how much the factor of nationality plays into classification. | |
| Mar 10, 2021 at 14:07 | history | answered | Maarten Buis | CC BY-SA 4.0 |