5
$\begingroup$

This answer just seems plain wrong to me.

https://stats.stackexchange.com/a/501/39632

The question states that there are more features than observations, so backwards stepwise selection (which would require fitting the full model, which would not converge) just doesn't seem doable.

However, two considerations.

  • The author is a diamond mod, so as a junior member of CV I would err on the side of being deferential, and someone already pointed out the problem. The author's response didn't make a lot of sense to me. ("This is machine learning, so you can.")
  • If the question were not a CW I think I would just -1 it, +1 the existing objection, and move on. In this case though, I am wondering whether the traditional injunction against editing someone else's answer in a way that is inconsistent with the intent still holds here. (Related question, but not on CW answers: Should I edit a factual error?)
$\endgroup$
6
  • $\begingroup$ On the statistical issue see e.g. stats.stackexchange.com/a/151305/17230. $\endgroup$ Commented Apr 5, 2016 at 13:46
  • 1
    $\begingroup$ Perhaps mbq's idea was to use some weak regularization (e.g. L2) to fit the full model? This could work then. $\endgroup$
    – amoeba
    Commented Apr 5, 2016 at 14:20
  • 2
    $\begingroup$ Also, I don't see a "factual error" that you can "correct". How do you want to edit this answer? To strike everything through and to append "This is wrong" in big letters on top? That does not sound like a good edit. $\endgroup$
    – amoeba
    Commented Apr 5, 2016 at 14:21
  • $\begingroup$ @amoeba: Yes - that would apply even if it were CW "proper". $\endgroup$ Commented Apr 5, 2016 at 14:23
  • $\begingroup$ @amoeba: I added a comment to the question that might help. $\endgroup$ Commented Apr 5, 2016 at 14:41
  • $\begingroup$ @Scortchi: I guess you meant "to the answer". I upvoted. $\endgroup$
    – amoeba
    Commented Apr 5, 2016 at 15:53

1 Answer 1

5
$\begingroup$
  • You don't need to defer to moderators' opinions on statistical issues.

  • We abuse the CW feature to allow questions that don't meet our guidelines, but which nevertheless we like for some reason or other - in particular "big list" questions. This is an example.

So the advice at Should I edit a factual error? applies.

$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .