Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: -kaplansky- available from SSC


From   n j cox <n.j.cox@durham.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: -kaplansky- available from SSC
Date   Mon, 28 May 2007 15:51:06 +0100

Thanks to Kit Baum, a program -kaplansky- has been posted on SSC.
Stata 8 is required. You should instsll with -ssc- if interested.

-kaplansky- is a revision of a program posted on 10 May in
a thread on whether generated normal (Gaussian) distributions
really do have skewness 0 and kurtosis 3 (with the definitions
of those measures used by -summarize-):

http://www.stata.com/statalist/archive/2007-05/msg00357.html

The name -kaplansky- is easily explained. -kaplansky-
graphs some examples of distributions with various values of
kurtosis discussed by Kaplansky in 1945. The intent is cautionary: values of kurtosis higher and lower than the Gaussian or normal value are consistent with various peak and tail properties.

The program now posted is more versatile than that posted on 10
May and there is, naturally, now a help file with details of
the distributions in question and a vignette, Stata manual-style,
on Irving Kaplansky (1917-2006).

A vein in the literature centres on the rather fuzzy question
"What is kurtosis?". Many people want it to mean one thing they can
wrap their mind around (peakedness, say), but one of Kaplansky's
maxims was to look at examples as a way of saving yourself from misunderstandings. He didn't plot his densities, but that's something
that's easily done.

Nick
n.j.cox@durham.ac.uk
*
* 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