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

st: RE: Graphing advice


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Graphing advice
Date   Tue, 16 Jul 2002 23:03:02 +0100

Christopher Auld
>
> I wonder if anyone could give me some advice on how to best
> graphically
> present some results, hopefully using Stata.  I have 3 parameters of
> interest and 4 estimators.  I have been asked by an editor
> to create "a
> graph or two" summarizing the results. I would like to
> display both the
> parameter estimates and their standard errors, which are based on
> asymptotic approximations.  Box plots seem to be overkill since the
> distributions are normal.  I don't see how to use bar charts to
> conveniently display both the coefficients and standard errors.
>
> Any suggestions?
>

First off, I recommend horizontal displays,
because you will want some text as explanation.

Your data structure sounds something like

parameter estimator      (est - k * se)    est   (est + k * se)
1            a
1            b
1            c
1            d
2            a
2            (etc.)
2
2
3
3
3
3
4
4
4
4

Cleveland's dot plots (dot charts) should
be excellent. Check out his 1993, 1994 books
(references in Stata manuals). The
parameter and the estimator could make up the
legend and the three numbers in each case
what is shown in the data region.

There is a Stata implementation: -hplot-
on SSC.

Among many other references:

Gelman, A. and friends. 2002. Let's practice
what we preach: turning tables into graphs.
The American Statistician 56, 121-130.

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