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

Re: st: Re: RE: Error bars on bar plots


From   "R. Allan Reese" <R.A.Reese@hull.ac.uk>
To   george hoffman <ghoffman@mcw.edu>
Subject   Re: st: Re: RE: Error bars on bar plots
Date   Mon, 30 Jun 2003 09:56:25 +0100 (BST)

At a risk of inflaming the situation and being branded a Luddite, I'll add
a comment:

On Fri, 27 Jun 2003, george hoffman wrote:
> 1. report means and sd's of groups and means comparison s(anova with
> post-tests)
> 2. graph the means and sd's with bar (or other symbols) and error
> bars.
> 3. options to graph se's or ci's.
> -currently using joanne garrett's predxcat.ado with modifications to
> do the above, but bars are not an easy option.

Request 1 seems to ask for a command that incorporates the analysis with
drawing the graphic.  It has always seemed to me a strength of Stata that
it distinguished the operations: eg, you did fit / predict / graph to draw
a scatterplot with regression line.  Recent and current trends seem to be
reversing this policy, which is fine for those who need to do repeated
standard operations, but dangerous whenever *real* data are analysed.
Hence I would rather stick to and articulate the old policy, and point to
the portmanteau procedures as conveniences.

Hence request 3 should be interpreted as providing an option for hi-lo
lines, which in specific cases may be SEs or CIs.  That also reminds the
user to *note in the caption* which they are.


R. Allan Reese                       Email:     r.a.reese@hull.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