English Wikipedia @ Freddythechick:Articles for deletion/Masreliez’s theorem

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 delete. Notability isn'tclearly established but there seems to be some consensus that a new more focused article might be more acceptable then the current one Spartaz ^Humbug! 03:46, 28 December 2010 (UTC)

Masreliez’s theorem

(Find sources: Google (books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL)

WP:COI article by Masreliez promoting his estimation of Kalman filtering. Not generally a notable algorithm and not encyclopedic. jps (talk) 03:30, 20 December 2010 (UTC)

Delete Unnotable result by unnotable person. Given details on user page and editing history across multiple other wikipedias, probably self-written. Mathsci (talk) 10:18, 20 December 2010 (UTC)
- How does one know whether it's a notable result or not, without knowing its content? The article fails to say what Masreliez’s theorem says. Michael Hardy (talk) 02:21, 21 December 2010 (UTC)
  - I did a search on Mathscinet under "anywhere" with the keyword "Masreliez". There were nine results, including four papers by the author. The paper containing the theorem has not been reviewed on Mathscinet, but is cited in 3 subsequent notes. In Zentralblatt, I found 15 results for the name with a similar search. The author's summary of the 1975 paper is reproduced in a scanned version of Zentralblatt. [1] There are four citations which reproduce the three citations in Mathscinet, plus a second citation by the author Cipra (with Rubio) from a paper which was not reviewed on Mathscinet. Mathsci (talk) 18:43, 21 December 2010 (UTC) cses where either 1)
    - So what does the theorem actually say? Michael Hardy (talk) 00:22, 22 December 2010 (UTC)
      - Did you not click on the link to the author's summary at Zentralblatt? "Two approaches to the non-Gaussian filtering problem are presented. The proposed filters retain the computationally attractive recursve structure of the Kalman filter and they approximate well the minimal variance filter in cases where 1) the state noise is Gaussian or its variance small in comparison to the observation noise variance or 2) the observation noise is Gaussian and the system is one step observable. In both cases the state estimate is formed as a linear prediction corrected by a nonlinear function of past and present observations. Some simulation results are presented." (4 pages, IEEE automatic control, 1975) Mathsci (talk) 08:17, 22 December 2010 (UTC)
Comment. I am afraid this is just foul tactics in jps’ initiated battue at Masreliez associated edits. Jps takes fright at any edit that might give C. Johan Masreliez credit as a notable person also doing well received mainstream science. Please also note personal attacks here. ¨( Kurtan (talk) 00:44, 23 December 2010 (UTC)
Keep. Remarkable unsupported allegations and conclusions. I am NOT Masreliez or his puppet. I am living in Stockholm, Masreliez in Seattle, USA!

Why should I not list it on the Swedish, Japanese and Spannish wikis, as I use to edit there since years, if I find it a notable idea?? Is it really neccessary to list all 144 citations to the follow up article by Masreliez & Doug Martin (1977)? /Kurtan (talk) 14:17, 20 December 2010 (UTC)

Delete: a minor mathematical theorem, that (like much such work) builds upon earlier work & has been built upon by later work. No indication that this theorem has received "significant coverage in reliable sources that are independent of the subject", just occasional discussion in derivative primary literature, and the odd passing mention in the secondary. Hrafn^Talk_Stalk^(P) 14:35, 20 December 2010 (UTC)
- Maybe, but at stake here is its role in robust statistics. I use to support the number of followers with 50 third party relevant references from Academic Search, which I reckon a reliable source, at least to give a sense of not being minor... /Kurtan (talk) 20:57, 23 December 2010 (UTC)
Note: This debate has been included in the list of Science-related deletion discussions. -- • Gene93k (talk) 18:05, 20 December 2010 (UTC)
Delete for reasons above. May be too early. Xxanthippe (talk) 22:10, 20 December 2010 (UTC).
- 190 citings as you mention below should be "significant coverage in reliable sources that are independent of the subject". Eponym status should also add to notability as should the impact on follow up papers on robust estimation and its applicability over the notable Kalman filter range. /Kurtan (talk) 00:44, 23 December 2010 (UTC)
Keep. I don't know what the allegation of COI is based on, but in any case COI is not by itself a ground for deletion. The citations produced by Google scholar and Google books show sufficient notability. The treatment leaves ample room for improvement, but that's what Wikipedia is for; it's not so bad that it cannot be improved and needs to be deleted. --Lambiam 23:28, 20 December 2010 (UTC)
Keep. Seriously, did the people !voting delete even attempt to search for the subject. Apparently some people find this notable enough to mention in an abstract for published lecture notes. [2] Which is just one of the more than 200 hits on google scholar.TimothyRias (talk) 09:39, 21 December 2010 (UTC)

Martin, the person who mentioned it in 1979, was a coauthor of another short note. Mathsci (talk) 23:00, 21 December 2010 (UTC)

Keep. Clearly notable enough for Wikipedia. Just needs a lot of work. Melcombe (talk) 16:15, 21 December 2010 (UTC)
Comment. A problem is that no general consensus has emerged as to how much a theorem has to be cited to become notable. The GS cites for Masreliez's paper appear to be 190, which is not at all high compared to some of the figures that appear on these pages. It may not be useful to have an article on every paper with 190 cites or more. Xxanthippe (talk) 06:22, 22 December 2010 (UTC).
Delete as not notable. There needs to be evidence of articles about rather than just mentioning this theorem. There are 11 Google Scholar hits for this linked above, as opposed to at least a thousand for "Rolle's Theorem", "Rouche's Theorem", "Lagrange's Theorem". At the same time, I'm not convinced by the argument about it building on other work. After all, Fermat's Little Theorem is a special case of Euler's Theorem is a special case of Lagrange's Theorem, and yet we quite rightly have articles on all three. Notability is the criterion here. Zarboublian (talk) 09:46, 24 December 2010 (UTC)
Notability yes, but it is established not so much by the name of theorem, but rather by the name of its paper, which on Google Scholar gives 161 hits (and the 190 citations). This means that most scientists are not aware of a title of the theorem (1975), but well on its scientific implication. I found this notable enough for my edits on the Japanese version and would vote for “Keep” here as well. (+4 st ~) — Preceding unsigned comment added by Mariguld (talk • contribs) 21:24, 26 December 2010 (UTC)
Delete or possibly userfy if someone is willing to work on it. We can't allow an article on a theorem which doesn't state the theorem. It isn't even clear from the current article that the object is really a theorem or an algorithm. I have enough background to understand what the algorithm might be doing but the article clearly needs a very large amount of work. Even after a lot of work we could still argue about Wikipedia notability, but I hope that we could find a home on some wiki for a clear statement of this algorithm if (and only if) it allows someone with a basic knowledge of Kalman filtering and robust statistics to understand it. Dingo1729 (talk) 18:26, 27 December 2010 (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.