Talk:Seven-number summary

The Bowley citation is inexact and the reference incomplete. The citation, p.62, of the 1910 edition:

Suppose we wish to test the knowledge of a large class of students (say 100). We might by some very simple examina- tion, or by consulting the teacher, place them roughly in order of intelligence, and then examine in detail, say Nos. 1, 10, 25, 50, 75, 90, 100 (the maximum and minimum, median, quartiles and two deciles)."|' Thus a good estimate could quickly be obtained, and the relative ability of two similar classes quickly judged.

The footnote does refer to "position," but not, it seems, in a way that establishes the seven measures as "the" seven positions.

Maybe we should add a link to Cornell's university scanned exemplar?

http://www.archive.org/details/cu31924013702950 )

The whole section on the parametric summary is a bit confusing. It is perfectly possible to take the percentiles of a non-normally distributed variable but they will only be equally spaced if the variable is normally distributed. Indeed, the section says that you can use this summary as a check on normality. So, this needs some cleaning upPeterLFlomPhD (talk) 20:10, 18 July 2015 (UTC)

parametric statistics
>>> The whole section on the parametric summary is a bit confusing. It is perfectly possible to take the percentiles of a non-normally distributed variable but they will only be equally spaced if the variable is normally distributed.

I second that point. The 2%-tile is as non-parametric as the 10%-tile. — Preceding unsigned comment added by 176.142.31.250 (talk) 10:51, 19 November 2018 (UTC)

Removed the characterization as parametric. — Preceding unsigned comment added by 176.142.31.250 (talk) 14:29, 7 May 2020 (UTC)