# What should the "best practices" tag be for?

There is a tag which currently has no usage guidelines. Currently it mostly seems to be used on questions which are very broad, particularly where there might be multiple approaches (e.g. project management, data analysis, modelling strategies, how to write code).

I have had a couple of edit requests in the review queue asking to add the tag to various questions, and in the absence of usage guidelines it isn't completely clear where it would be appropriate.

On this question, I could understand why the tag was being added (the question includes the phrase "Is this an example of semi-supervised classification and what are good approaches one can take to this kind of problem?"). I rejected the edit in that case, as the question seems rather too specific compared to other questions with the tag. I felt that if this question deserved a "best practices" tag, then almost all questions should - after all, don't most questions (at least about plotting and data analysis; mathematical statistics or probability not so much) want to know what would be "best practice" in their situation?

On this question I felt that "what is a sensible way to approach" determining "if the missing data are 'missing at random' or 'missing not at random'" seemed sufficiently broad to make the tag worthwhile.

But on reflection it is hard to see how to make a principled decision about this, and I can understand that other people might not draw the same distinction that I did.

I'd like to see if there's community consensus on what usage guidelines should be for [best-practices]. It seems to make particular sense in situations where there are a variety of practices but some of which are generally deemed superior to others (for instance, in regression modelling, stepwise regression is regarded as "not best practice"). But I can't see obvious black and white limits about where the domain of "best practice" should end. If it were applied to every question where, at some stage, an analyst has to make some sort of choice between methods, then it would become one of the most frequent tags on the site - but its value in identifying content related to professional practice (which is the use it currently seems to serve) would be almost entirely diluted. Although at the moment it does seem to serve some kind of (undefined!) purpose, I can even see an argument for getting rid of it entirely, if it turns out to be impossible to pin down.

Update (Dec 21): All threads that had [best-practices] as the only tag have been re-tagged. This tag would now be ready to be burninated (by SE admins) if community agrees.

• Looking at the lits of all 59 questions tagged with [best-practices] I cannot detect any coherent system. If [best-practices] is supposed to mark threads (related to some analysis choices) of "high importance", then (a) it's definitely failing to do so (there are lots of poor threads with this tag), and (b) arguably cannot and should not serve such a purpose anyway (because no tag should). It looks like it might better go the way of big-list... Good that you raised this issue. Nov 5 '15 at 22:37
• @amoeba Unless someone can come up with a plausible usage guideline then I am inclined to agree. It is possible, of course, to define guidelines that are stricter than the ones that are currently tagged, and then remove those which would not fit the proposal. But I haven't included a clear proposal in my question because, like you, I struggled to find something coherent. Nov 5 '15 at 22:54
• I found about the best practices tag recently and used it. I think is should be used on question that can be a a hub of answers of some general area (like coping with imbalanced data sets). I agree that that is no clear definition of the tag and when to apply it. However, I think that having such a tag will be very beneficial. If you feel that the best-practices tag is not the appropriate one, maybe we should create a new tag for that peruse with a clearer definition.
– DaL
Nov 6 '15 at 6:21
• @Dan A "question that can be a hub of answers of some general area" should certainly be closed as too broad. So it sounds like it serves the very useful purpose ... it's a tag that says "close me". Nov 11 '15 at 8:48
• Well, any usage can be a justification for the tag. ;-) Is the concept of a "survey tag" (like survey papers) acceptable?
– DaL
Nov 11 '15 at 9:22
• This tag is undoubtably a residual from StackOverflow. I don't think there's an exact parallel to this in the world of statistics. I also think that's a shame. Nov 23 '15 at 0:09
• The [big-list] is now gone, by the way. Nov 26 '15 at 15:01
• Today I came across [basic-concepts] tag with 200+ questions. Looks like another useless meta tag to me, or what do you think? Dec 4 '15 at 22:45
• @amoeba It sounds it to me. Think that might need a whole new meta thread, though this one does not seem to have come to much of a conclusion. (Though pretty much everyone seems to be in favour of getting rid of "best-practices", I am not sure how this would be turned into some sort of implementation.) Dec 4 '15 at 22:50
• I went through all the questions where [best-practices] or [basic-concepts] were the only tags and re-tagged those. I think both these tags are now ready to be burninated, if the community approves of that. I've just put [burninate-request] tag on my meta thread re basic-concepts; I'd say we should put it here too. Dec 20 '15 at 0:40
• It seems, nothing happened after your last update. I'm willing to gradually remove those tags, if you think it is appropriate. Just let me know. Tks. Aug 2 '16 at 19:09
• @andre thanks, I accepted your answer Aug 2 '16 at 19:51
• @Andre I'm not sure whether [rule-of-thumb] actually is especially "meta" (any more than e.g. [intuition] is) ... but I can see that being something other people might come to different conclusions on. So might be worth a post. (Personally I'd suggest keeping that one, I think it is rather clearer in purpose and more useful than "best practices".) Aug 5 '16 at 14:27
• Done (cc/ @amoeba). Sep 19 '16 at 22:42
• @glen_b Indeed - I did tentatively suggest some of the better threads might benefit from a "professional-practises" tag or similar. It seemed that it was more "how we go about a data analysis task" rather than "how do I do the underlying statistics". But probably more specific tag names would be better. We already have "project-management" for instance Sep 21 '16 at 9:00

Update: the tag was burninated.

In my opinion, 'best-practices' is a meta tag and should go. On contrary to 'self-study' it does not have a clear scope which would justify keeping it here. In summary, it is what you said:

.....but its value in identifying content related to professional practice (which is the use it currently seems to serve) would be almost entirely diluted....

I'd rather see 'best-practices' leaving, without needing a substitute tag.

• I think this is perfectly reasonable as an alternative. My argument is essentially that "professional practice" seems (to me) to be easier to pin down and captures something of the spirit of a certain subset of these questions that may be worth connecting together; "best practices" seems more akin to pinning jelly to a wall with your left shoe. Nov 9 '15 at 16:58
• +1 for getting rid of [best-practices]. As I wrote in a comment to Silverfish'es answer, [professional-practice] (if created) will hardly be a substitute for [best-practices]: most of the threads currently tagged with [best-practices] are outside of the scope of [professional-practice]. Nov 9 '15 at 22:16
• +1 ... Incidentally (if a bit off topic) a tag like self-study needs constant attention. They do serve a purpose but they're a lot of work. Nov 11 '15 at 8:50

Based on the difficulty formulating a clear scope for , and the comments that it seems to be a "meta" tag (which is generally not considered best practice), there seems to be a strong case for getting rid of this tag.

I wonder whether questions like the following might benefit from something like as an alternative:

The scope for this would be something along the lines of "issues specifically relevant to the working practices of a statistician or analyst, but not necessarily a question that is statistical in nature". We certainly have historically accepted questions that might otherwise have belonged on Workplace SE, Academia SE or even Lifehacks SE, except that they were most relevant for people working in the field of statistics or data analysis.

• I'd rather see 'best-practices' leaving, without needing a substitute tag. Nov 9 '15 at 13:12
• @andre Post that as an answer, I think it is a perfectly reasonable alternative. Nov 9 '15 at 14:52
• I have edited my answer, so people who upvoted me earlier but may now prefer to vote for Andre's answer can do so. Nov 9 '15 at 17:08
• +1 for getting rid of [best-practices]. Having [professional-practice] is maybe not a bad idea, but it seems that its intersection with the current usage of [best-practices] will be only very cursory. Most of the threads currently tagged with [best-practices] are outside of the scope of [professional-practice]. So it appears to be an almost unrelated issue. Nov 9 '15 at 22:13
• @amoeba I get the feeling that, by some margin, P(professional-practice|best-practices) > P(professional-practice) but you are right that P(professional-practice|best-practices) would still be fairly small (well below 0.5) Nov 9 '15 at 22:18