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

st: RE: Standard deviation error bars


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Standard deviation error bars
Date   Tue, 23 Mar 2004 19:19:09 -0000

There have been several threads on Statalist on related 
questions since the release of Stata 8, ranging from whether 
this is a good idea to how you might do it. Recipes for "error
bar on measurement bar" plots (or what Paul Seed calls 
detonator plots) appear popular with some groups of biological 
scientists, and perhaps others, unpopular with those who think that 
the medium muddies the message.  

You should search the archives to see more. 

A partial summary on how it might be done: 

-graph bar-, -graph hbar- and -graph dot- don't lend themselves 
to added extras. 

-dotplot- has its own idea of showing mean +/- s.d. 

-serrbar- is always there. 

There is more scope for doing what I think 
you want by superimposing a -twoway rcap- on 
a -twoway bar-. Building on a suggestion by 
Stephen McKay, there is some code at 

http://www.stata.com/statalist/archive/2003-06/msg00631.html

Roger Newson has his own way of doing it on -eclplot-. 

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

Ward Hagar

>  Is there an easy way to put standard deviation error bars on 
> bar graphs and dot graphs?

*
*   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