home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!wupost!waikato.ac.nz!maj
- From: maj@waikato.ac.nz
- Newsgroups: bit.listserv.edstat-l
- Subject: Re: quartiles
- Message-ID: <1992Dec22.091245.12937@waikato.ac.nz>
- Date: 22 Dec 92 09:12:45 +1300
- References: <2328.9212211506@atlas>
- Organization: University of Waikato, Hamilton, New Zealand
- Lines: 25
-
- In article <2328.9212211506@atlas>, F.R.Jolliffe@GREENWICH.AC.UK (jf0zxt) writes:
- > Re quartiles -
- >
- > There is an argument for finding the first quartile at position n/4+1/2,
- > the median at n/2+1/2 (the usual position) and the third quartile at
- > position 3n/4+1/2 in my paper:
- > The principle underlying quartiles - a guide for the teacher. Maths. in
- > School, Nov. 1991, 20, 5, 30-32.
- >
- [deletions]
- >
- > (Mrs) Flavia Jolliffe
- > School of Maths., Stats., and Computing,
- > University of Greenwich,
- > London, SE18 6PF
-
- I havn't looked at your paper, but this definition would have a
- strange consequence: if all the signs of the data were changed
- the new L1 would not be minus the old L3, etc.
- --
- Murray A. Jorgensen [ maj@waikato.ac.nz ] University of Waikato
- Department of Mathematics and Statistics Hamilton, New Zealand
- __________________________________________________________________
- 'Tis the song of the Jubjub! the proof is complete,
- if only I've stated it thrice.'
-