Talk:Percentile

From Citizendium
Revision as of 16:18, 26 February 2010 by imported>Chris Day (pasted talk outlining move from quintile to percentile.)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search
This article is developing and not approved.
Main Article
Discussion
Related Articles  [?]
Bibliography  [?]
External Links  [?]
Citable Version  [?]
 
To learn how to update the categories for this article, see here. To update categories, edit the metadata template.
 Definition A statistical parameter separating the k percent smallest from the (100-k) percent largest values of a distribution. [d] [e]
Checklist and Archives
 Workgroup category Mathematics [Categories OK]
 Talk Archive none  English language variant British English

Replacing WP

I replaced the WP import by a new article, and added an example (test results) previously inserted by Anh Nguyen (3rd revision, 10:11, 8 November 2006). Peter Schmitt 16:03, 23 November 2009 (UTC)

Not quite so

The implication

is not always true; when k is at the left endpoint of the relevant interval, the first inequality is not strict; and when k is at the right endpoint of the relevant interval, the second inequality is not strict. In addition, I did not understand from the article, is k assumed to be integral, or not? If it is then these non-strict inequalities become more rare cases, but still possible. Boris Tsirelson 19:11, 26 November 2009 (UTC)

Thank you for spotting the p's. I changed from p to k and forgot them.
Yes, I think that percentiles are used for integer k. I am no statistician, so I cannot be absolutly sure. But I have two reasons to assume that integer values are the usual case (though everybody who understands them will understand arbitrary values):
They are usually called "k-th percentile.
For general probabilities there is the quantile.
And, yes, I overlooked the special case in the inequality. It should be "or" instead of "and".
Peter Schmitt 00:57, 27 November 2009 (UTC)

Another remark. It is written correctly "...in a population (or a sample)", but afterwards, all formulas are written in terms of probabilities, not frequencies. It would be cumbersome to write each formula in two forms. However, it could be explained to the reader that each formula has two, or even three, interpretations: (a) probabilities are given by a "theoretical" (often, continuous) distribution; (b) probabilities are frequencies in a finite population, and correspond to a random choice of one element from the population; (c) probabilities are frequencies in a sample, and correspond to a random choice of one element from the sample, which is related to bootstrap (resampling). Boris Tsirelson 10:13, 27 November 2009 (UTC)

(Quintile) Candidate for deletion?

This article was originally a Wikipedia disambiguation page. But none of the articles to which it pointed exist on CZ, so I removed the links to them, and removed the disambig template. Now the page is not much more than a definition, which would seem to make it deletable, but I'll leave that up to those who have the authority to make such decisions. Bruce M.Tindall 16:34, 5 April 2007 (CDT)

I replaced this by a redirect to Percentile. As Bruce said, this page was poor in content, moreover, it was a WP import without credit, and not enough changes for the indicated status "stub". Finally, there is no need to explain "quintile" separately. --Peter Schmitt 14:01, 21 January 2010 (UTC)