Statalist


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

Re: st: RE: bihistogram


From   Ronan Conroy <rconroy@rcsi.ie>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: RE: bihistogram
Date   Wed, 27 Aug 2008 15:23:32 +0100

On 27 Aug 2008, at 12:16, Rajesh Tharyan wrote:

Hi sorry about the post with no link. Not sure what happened

http://www.itl.nist.gov/div898/handbook/eda/section3/bihistog.htm

Looking at this, I am still not sure that this is the best way of displaying the data. For several reasons

1. Histogram shape is notoriously sensitive to the width and starting position of bins.
2. The eye is better at comparing side-by-side plots where position on the same scale is used to make the comparision
3. A histogram does not show the data
4. A histogram cannot be used to infer descriptive statistics

I would recommend, as an alternative, Nick Cox's -stripplot- with - vertical- and -box- options. Suddenly you see far more of the data, and are in a far better position to make comparisons.



Ronan Conroy
=================================

rconroy@rcsi.ie
Royal College of Surgeons in Ireland
Epidemiology Department,
Beaux Lane House, Dublin 2, Ireland
+353 (0)1 402 2431
+353 (0)87 799 97 95
+353 (0)1 402 2764 (Fax - remember them?)
http://www.flickr.com/photos/ronanconroy/sets/72157601895416740/

P Before printing, think about the environment




*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* 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