7
$\begingroup$

is the 40th most popular tag, having been applied to 1820 questions so far. But I quickly scanned through a handful of the tagged questions and it didn't seem particularly helpful in any of them. Also, there's no usage guidance and the tag description is quite vague:

A statistical model is a formalization of relationships between variables in the form of mathematical equations. A statistical model describes how one or more random variables are related to one or more random variables. The model is statistical as the variables are not deterministically but stochastically related.

Is there a purpose to this tag that I'm missing, and if so, can we edit the tag info+guidance to reflect that? And if it is not useful, how can we best deal with it?

$\endgroup$
9
$\begingroup$

I agree that the tag is pretty much useless because it is too unspecific and too vacuous. It is not the only tag like that. For example we have ×600 and ×900, which are also vacuous and could well be burninated & blacklisted as far as I am concerned. Some have argued that ×12,000 is an even more extreme example: How to improve the description and usage of the [machine-learning] tag?

That said, I do not think there is anything we can do about such tags: they are too popular for manual deletion and our community has never ever requested SE admins to burninate an existing tag.

So these tags are here to stay. The only thing we can do is to add something like

ALWAYS ADD A MORE SPECIFIC TAG.

to the tag wiki excerpt.

$\endgroup$
  • 1
    $\begingroup$ Thanks, that makes sense. Is there a reason we never burninate tags (I can ask that as a separate question too)? $\endgroup$ – mkt Jun 26 at 10:51
  • 4
    $\begingroup$ Hard as I tried, I could never find out what the reason is: stats.meta.stackexchange.com/questions/3147. $\endgroup$ – amoeba Jun 26 at 11:28
  • 2
    $\begingroup$ In my dreams ;-) I have imagined implementing a system in which the application of certain tags by the OP automatically raises a notice (for all to see) announcing that this person hasn't a clue what they're asking about :-) and automatically downvotes the post, thereby doing most of our work for us. However, some of the people who apply modeling, fitting, mathematical-statistics, and so on, actually know very well what they're doing. $\endgroup$ – whuber Jun 26 at 14:34
  • 5
    $\begingroup$ @whuber: can't you build a Machine Learning tool to do that? (runs for cover) $\endgroup$ – Stephan Kolassa Jun 26 at 15:06
  • 2
    $\begingroup$ @whuber It sounds like you are against burnination. If so, what course of action would you suggest for tags like this one? Are they worth retaining in their present form? Or adding the text suggested by amoeba, which seems like quasi-deprecation? $\endgroup$ – mkt Jun 26 at 15:35
  • 2
    $\begingroup$ In the absence of further information from the mods, I'm accepting this answer and have edited the relevant wiki tag guidance with your suggested text. $\endgroup$ – mkt Jul 1 at 18:40

You must log in to answer this question.

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