In my opinion there should be at least the following two tags, I couldn't find:

  • "Time Series",
  • "Functional Data Analysis".

Since functional data are used more and more and time series as a discipline are very popular, it could be considered to have the following tag as well:

  • "Functional Time Series".

What do you think about that?


  • $\begingroup$ Are there any existing questions which for which these tags would be appropriate? Tags cannot exist unless they are attached to questions. $\endgroup$ – user642796 May 25 '16 at 14:40
  • $\begingroup$ I could have asked a couple of questions, but there haven't been appropriate tags for doing that. $\endgroup$ – Obriareos May 25 '16 at 15:57
  • 2
    $\begingroup$ How has the lack of tags prevented you from asking the questions? $\endgroup$ – Tobias Kildetoft May 25 '16 at 19:56
  • $\begingroup$ Good question: It hasn't. But if these tags exist, it would be a lot easier to filter questions I am interested in, since I work on specific functional time series. $\endgroup$ – Obriareos May 25 '16 at 21:10
  • $\begingroup$ The onus is on you to demonstrate that these tags are actually desirable now. Again, a tag cannot exist without being attached to a question, so unless you can demonstrate on-topic questions existing now that would benefit from having this tag there is little discussion left to have. $\endgroup$ – user642796 May 26 '16 at 4:07
  • $\begingroup$ E.g. two of my posts ("Hadamard Product (Schurproduct)" & "When is an selfadjoint operatorvalued matrix with positive semidefinite diagonal elements positive semidefinite as well?"). I didn't explicitly mentioned that it has something to do with functional time series, but the ones dealing with functional time series would have noticed why I was asking that immediately and could have given an appropriate answer quicker. The other reason is that I need these tags for future questions. $\endgroup$ – Obriareos May 29 '16 at 17:31

Both (time-series) and (functional-data-analysis) tags exist at Cross Validated ... are there so many non-statistics uses of them that it justifies adding them here as well?

  • $\begingroup$ Thanks for you hint. However, I think the tags should exist, since "Cross Validated" seems to be very focused on application. If you take a look at papers (e.g. from Denis Bosq) dealing with Functional Autoregressive Processes you will see it is an "own world". It doesn't really fit into "Functional Analysis", "Statistics" or "Operator Theory". $\endgroup$ – Obriareos May 25 '16 at 16:05
  • $\begingroup$ You need more pros? I would like to get this question answered. Thank you! $\endgroup$ – Obriareos Jun 12 '16 at 14:19

You must log in to answer this question.

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