So we have , with 6 questions tagged. Three also have tagged, and all the questions were posted this year.

Simple question, is it desirable? There's also tag for example. If there's a consensus for it I'll try to improve the tag (and retag questions that deserve it).

But I can see arguments for it, as exists.

  • 3
    $\begingroup$ I would say, [sample-variance] should be removed and replaced by [variance], and unless somebody protests here, you can go ahead and do the edits. $\endgroup$ – amoeba says Reinstate Monica Sep 20 '16 at 15:04
  • 3
    $\begingroup$ I am not sure but perhaps we could consider merging [sample-mean] into [mean]. I don't immediately see what it adds, and lots of the questions tagged with [mean] are presumably about sample means. $\endgroup$ – amoeba says Reinstate Monica Sep 20 '16 at 15:05
  • 2
    $\begingroup$ Finally, why did you mention [estimation]? I don't understand your 2nd paragraph. What does it have to do with sample-variance? $\endgroup$ – amoeba says Reinstate Monica Sep 20 '16 at 15:06
  • $\begingroup$ So, apparently we have 3 options regarding [sample-variance] and [sample-mean]: i) do nothing; ii) make them synonyms of [variance] and [mean], respectively; iii) manually edit posts to remove them (burninating)? Is that it? $\endgroup$ – Andre Silva Sep 20 '16 at 15:32
  • 2
    $\begingroup$ @amoeba I mean double tagging variance and estimation as a substitution for sample-variance $\endgroup$ – Firebug Sep 20 '16 at 16:38
  • 2
    $\begingroup$ @AndreSilva sample-variance has 6 threads and can be taken care of in two minutes. In contrast, sample-mean has 100+ threads, that's why I suggested to make a synonym instead of manual retagging. $\endgroup$ – amoeba says Reinstate Monica Sep 20 '16 at 17:10

Following the discussion in the comments, I have removed from all threads. The tag will be automatically deleted within 24h.

I note that the wiki excerpt for our tag explicitly says that it should be used for sample variances:

The expected squared deviation of a random variable from its mean; or, the average squared deviation of data about their mean.

  • $\begingroup$ Actually, I can see that people who use Excel (and some calculators and some elementary texts) would go "But the average squared deviation means an $n$ denominator. Excel says that's the 'population standard deviation' ... but I want sample standard deviation. Why isn't there a tag for it??" ... While we might all realize that the $n$ vs $(n-1)$ denominator thing isn't what makes a calculation a sample SD or a population SD, I think we should expect a large fraction of beginners to think otherwise. $\endgroup$ – Glen_b -Reinstate Monica Sep 29 '16 at 23:55
  • $\begingroup$ Do you think this concern can be addressed with some appropriate edit of the wiki excerpt? $\endgroup$ – amoeba says Reinstate Monica Sep 30 '16 at 22:34
  • $\begingroup$ Yeah -- at least to the extent that users read them, I think it would help. $\endgroup$ – Glen_b -Reinstate Monica Oct 1 '16 at 0:59
  • $\begingroup$ @amoeba and what about [sample-mean]..? The argument is actually the same, as you noted. $\endgroup$ – Tim Oct 2 '16 at 18:42
  • 1
    $\begingroup$ @Tim I posted it as a suggestion in our tag synonyms thread. Can you upvote it there? meta.stats.stackexchange.com/a/4363/28666 $\endgroup$ – amoeba says Reinstate Monica Oct 2 '16 at 18:56
  • $\begingroup$ @amoeba right, I see that I actually did it already... $\endgroup$ – Tim Oct 2 '16 at 18:57
  • $\begingroup$ ___ @Tim :-) ___ $\endgroup$ – amoeba says Reinstate Monica Oct 2 '16 at 18:59

You must log in to answer this question.

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