Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: RE: A simple but really hard question


From   Ronan Conroy <rconroy@rcsi.ie>
To   "statalist hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: RE: RE: A simple but really hard question
Date   Thu, 31 Oct 2002 09:49:11 +0000

on 30/10/02 9:43 pm, Li, Wenjun at WLi1@Lifespan.org wrote:

> Thanks, everyone. A friend has suggested to use "double-octiles" for
> quantiles based on division into 16 groups of equal frequency. How do you
> think about this?  "Sedeciles", as suggested by Nick Cox, is a possible name
> too.

How about sixteenths?

Cis-Atlantic music notation is bedevilled with medieval note-value names
called quavers and crotchets and demisemiquavers. The Germans brought to
America a simple system that calls notes whole notes, half, quarter etc.

I frequently refer to n-tiles as quarters, fifths and tenths. The system is
extensible. And, indeed, generating too many quantiles from a small dataset
produces fewtiles.

Incidentally, what happens if you divide your data into three groups based
on rank, send them down the New York drains and teach them martial arts?



Ronan M Conroy (rconroy@rcsi.ie)
Lecturer in Biostatistics
Royal College of Surgeons
Dublin 2, Ireland
+353 1 402 2431 (fax 2329)

--------------------

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index