Wikipedia

Wikipedia:Articles for deletion/Mathematical formalization of the statistical regression problem

< Wikipedia:Articles for deletion
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. — Aitias // discussion 03:09, 2 January 2009 (UTC)[reply]

Mathematical formalization of the statistical regression problem

edit
Mathematical formalization of the statistical regression problem (edit | talk | history | protect | delete | links | watch | logs | views) (delete) – (View log)

The article attempts to justify itself by saying "the theoretical study of the regression problem requires a precise mathematical context than that given in the Regression analysis article" and purports to provide that "context". That this sort of "context" is needed is nonsense. The article takes pains to define the random variables involved as measurable functions on a probability space, Kolmogorov-style, and seems to assert that that is needed for rigorous mathematical study of regression problems. That is false. Then the article entirely neglects any mention of statistical estimation of parameters or of the regression function, which is in fact essential to any regression problem (what's "least squares" all about??), or of hypothesis testing, etc. Just what is the role of the parameter θ? The article is offensively vague about that. The way of using it suggests that θ is a parameter to be estimated, but earlier in the article θ is a member of the ___domain of the underlying probability space. That is really serioius confusion at best. The article also asserts that the predictor variables are themselves random variables. In some cases that is true; in other cases they are determined by the design of the experiment and not random at all. In effect, the creator of the article appears to have wanted to show off his mastery of Kolmogorov-style notation while applying it to a statistical problem that he or she did not understand at all, and to assert, falsely, that that approach is needed in order to study regression problems. Michael Hardy (talk) 19:32, 30 December 2008 (UTC)[reply]

  • Delete. I don't mind so much that the article is vague and poorly written (which it is, to excess). But I do mind that this seems to be an unencyclopedic topic. At present, the article is a glorified dictionary definition, and I don't see how it'll ever grow beyond that. Ozob (talk) 19:57, 30 December 2008 (UTC)[reply]
Comment Wikipedia has no deadline WP:DEADLINE, so I don't think that's a valid reason for deletion.  LinguistAtLarge  21:34, 30 December 2008 (UTC)[reply]
  • Delete. Kolmogorov-style itself does not irritate me. However, the article is abortive, almost pointless, and after all, the last line is meaningless: the subtraction operation is not defined in a measurable space. Boris Tsirelson (talk) 20:54, 30 December 2008 (UTC)[reply]
  • Delete. I think there might have been a use for some of this stuff if someone were attempting to extend the idea of regression to some strange new probability spaces. But, since there is no sign of such material, it is useless. Melcombe (talk) 11:13, 31 December 2008 (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.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Wikipedia:Articles_for_deletion/Mathematical_formalization_of_the_statistical_regression_problem&oldid=1082620904"