- The following discussion is an archived debate of the proposed deletion of the article below. Please do not modify it. Subsequent comments should be made on the appropriate discussion page (such as the article's talk page or in a deletion review). No further edits should be made to this page.
The result was keep. There is a consensus to keep, the possibility of redirects can be discussed on the talk page. (non-admin closure) Szzuk ( talk) 12:30, 17 April 2018 (UTC)
1.96
- 1.96 ( | talk | history | protect | delete | links | watch | logs | views) – ( View log · Stats)
- (Find sources: Google ( books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL)
This number is an arbitrary approximation of an arbitrary constant; there is nothing here that should not be found at Normal distribution or Z score. CapitalSasha ~ talk 20:35, 9 April 2018 (UTC)
- Note: This discussion has been included in the list of Mathematics-related deletion discussions. The Mighty Glen ( talk) 06:35, 10 April 2018 (UTC)
- Keep looking at the page view statistics it gets about 200 hits a day, so some people must be interested. It a number a lot of people will have stuck in their heads as its the key number used to tell if a test passes at 5%, generally the level used in much of medicine where there you have limited trials.-- Salix alba ( talk): 09:01, 10 April 2018 (UTC)
- Comment - I think this article should/could be kept for now. I don't think this article needs to exist, not because it isn't significant (it is), but because this title isn't a very good one. At the last AfD, the title,
95 percent confidence interval in statistics, was suggested. Other titles such as "two standard deviations", "two standard deviations" (less accurate but still commonly used), etc. are also possible.
Normal distribution,
Z score, and
Confidence interval are, I think, not quite as good of a location for this material.
68–95–99.7 rule is possible, and I would support a merge there, I think. I am not sure, though, and would like to read what others think.
Smmurphy(
Talk) 14:30, 10 April 2018 (UTC)
- I would support a merge in principle but there is so little actual content in this article that I don't know what to merge. A line in
Confidence interval saying "the most common confidence interval is 95%" would seem to sum up the entire content of what's here.
CapitalSasha ~
talk 21:54, 10 April 2018 (UTC)
- Fair enough. I think 68–95–99.7 rule is the best destination, and the history section would be all that is merged. Smmurphy( Talk) 22:02, 10 April 2018 (UTC)
- I would support a merge in principle but there is so little actual content in this article that I don't know what to merge. A line in
Confidence interval saying "the most common confidence interval is 95%" would seem to sum up the entire content of what's here.
CapitalSasha ~
talk 21:54, 10 April 2018 (UTC)
Keep I think it's a good pithy title, for an important constant. To a mathematician, it's not as significant as pi, or e, but to users and writers of thousands of articles on applied statistics, it's significant. There's an article on pi of course, so 1.96 is legitimate. I suspect many of the 200 hits per day may be from people who don't know any other term to search for it under. A redirect under any of the other titles suggested would frustrate wikipedia readers, since it would be way down the page. I think the 68-95-99.7 rule is more obscure than 1.96. Now 95% is a redirect to Normal distribution, and it's a long way down the page before 95% is discussed. Numbersinstitute ( talk) 22:45, 10 April 2018 (UTC)
- The article on e is called e (mathematical constant), so maybe this would be clearer as 1.96 (statistical constant). Numbersinstitute ( talk) 12:12, 12 April 2018 (UTC)
- Keep but rename: it's hard to think what title is most appropriate here but I think it's important to note that the article's subject is not 1.96 or even 1.95996398454005423552, but z.025. Perhaps 1.96 (approximation) or z-value of 0.975 would work. I would be happy with 95 percent confidence interval in statistics but not 1.96 (statistical constant) (the constant in discussion is not 1.96). But in any case, I think the subject itself is notable. — Bilorv (c) (talk) 14:53, 14 April 2018 (UTC)
- Merge elsewhere and delete/redirect. Given all the other related pages, I don't think a page on the approximation 1.96 makes a notable contribution beyond them. The value 1.96 only applies to the Normal distribution, but 95% CIs are calculated on many other statistical distributions; so I don't think titles like 95 percent confidence interval in statistics would be suitable. The software section can be deleted per WP:NOTHOWTO. Tayste ( edits) 00:00, 16 April 2018 (UTC)
- Keep. It's something people would expect to find in an encyclopedia. This is reasonably clear for the main title; We can deal with title problems with redirects. DGG ( talk ) 04:27, 16 April 2018 (UTC)
- The above discussion is preserved as an archive of the debate. Please do not modify it. Subsequent comments should be made on the appropriate discussion page (such as the article's talk page or in a deletion review). No further edits should be made to this page.