Wikipedia: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 keep. Redirecting was also suggested, but this can be decided outside of an AfD. – Joe (talk) 11:16, 14 December 2017 (UTC)[reply]

Masreliez's theorem

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

The same rationale as caused deletion before still applies (this article was created by a sock of the original article and should never have been recreated out-of-process, but there we are), this article is substantively equivalent to the version that existed at the time of the last nomination (not deletion). The issue is that the theorem though referenced obliquely is basically just a statement about

WP:GNG jump. Primefac (talk) 01:37, 7 December 2017 (UTC)[reply

]

Note: This debate has been included in the list of Mathematics-related deletion discussions. L3X1 (distænt write) 02:07, 7 December 2017 (UTC)[reply]

Note: This debate has been included in the list of Sweden-related deletion discussions. L3X1 (distænt write) 02:07, 7 December 2017 (UTC)[reply]

Note: This debate has been included in the list of United States of America-related deletion discussions. L3X1 (distænt write) 02:07, 7 December 2017 (UTC)[reply]

Weak keep. Searching Google scholar for this exact phrase finds multiple publications by disjoint sets of authors, none of them Masreliez himself, that all appear to be about this topic: "A representation of the posterior mean for a location model", NG Polson, Biometrika 1991; "Kalman filter with a non-linear non-Gaussian observation relation", T Cipra & A Rubio, Trabajos de Estadistica 1991; "Non-Gaussian State-Space Modeling of Nonstationary Time Series: Comment: Robustness, Computation, and Non-Euclidean Models" RD Martin & AE Raftery, JASA 1987 (a top author in a top journal); etc. I think that's enough for the low bar of
WP:GNG. —David Eppstein (talk) 02:25, 7 December 2017 (UTC)[reply
]

If you check the last AfD, I think you'll find that a lot of the citations are a bit suspect. I think it is questionable as to whether this is a novel claim about Kalman filtering or whether it is just a restatement of something rather obvious about it. My inclination is to say that it is the later as the provenance and prevalence of the use of this idea in spite of Kalman filtering being a huge industry is rather weak as you point out. Could we compare it to other signal processing theorems that get more play? I can't find another example that is as obscure as this in Wikipedia. Why not just redirect to the article on filtering? jps (talk) 15:12, 12 December 2017 (UTC)[reply]

Comment It would sure help a lot if the article said what the theorem actually was. It's possible that it's the kind of result that would fit into another article, such as
talk) 17:04, 8 December 2017 (UTC)[reply
]

Weak Keep Severe content issues, but this does appear to unambiguously refer to a theorem by Masreliez published in 1975, and is cited enough.
π, ν) 21:21, 8 December 2017 (UTC)[reply
]

Buy why a separate article? jps (talk) 15:12, 12 December 2017 (UTC)[reply]

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.