7
$\begingroup$

I recently made a question that gathered no attention: Bootstrap and numerical optimization of statistic.

I think I've come up with a much simpler and to-the-point way of asking the same thing (posted below). My question here is, can I delete the old question (it doesn't have even a comment) and create a new one, or will this be seen as me trying to game the system?


New formulation of the question

Often times the bootstrap is used with a statistic that can be analytically evaluated (both in the real and the resampled datasets), e.g. the mean.

But if the statistic can not be analytically obtained (e.g., if we are maximizing a likelihood through some numerical optimization process), each bootstrap resample will contain an "extra" degree of uncertainty, as we are not really obtaining the true statistic for each resample but an approximation to it.

Does the bootstrap account for this "extra" uncertainty?

$\endgroup$
9
$\begingroup$

One clear principle has consistently helped me moderate such situations:

If your intended changes affect only your work, feel free to make them. Indeed, we encourage you to do so. But if they might affect the contributions of others, then be careful!

By "contributions of others" I mean principally answers that may have been posted in the thread, but I also include comments of substance. Thus, for instance, if anybody has answered (and especially if such an answer has been upvoted), then unilateral deletion of the thread is considered to be "self-destruction," which is not a good thing. The system actually flags such acts for moderator review. If there is a comment thread that illuminates the nature of the question, such as providing links to related materials, pointing out misconceptions, or whatever, then you should also be reluctant to take any action that would remove that material from public view.

In the present case, where a question has garnered no comments or answers, the best approach is to edit it. An edit puts the thread into the community's review queue, which will bring it to the attention of the many people who routinely review that queue.

$\endgroup$
  • $\begingroup$ I think it's impossible to self-delete a question that has an upvoted answer. $\endgroup$ – amoeba May 17 at 20:44
  • $\begingroup$ @amoeba That's a good point. I'm not completely sure about it though, because I haven't tested that proposition in a case where upvotes have been balanced by downvotes. $\endgroup$ – whuber May 17 at 21:20
  • $\begingroup$ Oh now I see your point. I think you are right: it's impossible to self-delete a question that has an answer with a positive score. If an upvoted answer has net score zero, then AFAIK it wouldn't prevent self-deletion of the question. $\endgroup$ – amoeba May 17 at 21:26

You must log in to answer this question.

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