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

st: RE: Need help w serrbar format


From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   st: RE: Need help w serrbar format
Date   Fri, 22 Jul 2005 19:55:08 +0100

You are between the Devil and the Deep Blue Sea here. 

-serrbar- is a bit of an historical hangover. It is not 
a general command for plotting results with errors, but 
just a codification of one recipe. In particular, horizontal 
alignment is wired in. 

In the absence of anything meta to your satisfaction, 
doing it yourself appears indicated. 

Nick 
[email protected] 

Garrard, Wendy M.

> I am having trouble producing a custom << serrbar >> but cannot find
> instructions for how to display the features I need. I have looked in
> the manuals, help files, and Statalist archives.
> 
> (1) make the graph vertical (default display is horizontal)
> (2) align the case/marker labels (study ID) on either the 
> left or right
> side of the graph
> (3) add one or two columns alongside the labels containing (a) effect
> size and (b) sample size. 
> 
> I am using the serrbar to create a forest plot of 32 effect 
> sizes for a
> meta-analysis. I am aware of the forest plots bundled with some of the
> user-written meta-analysis commands, but they do not meet my needs
> either, and seem less flexible for customizing than serrbar. 
> I would be
> happy to use either approach, just so it yields the graph I need.
> 
> The graph I am trying to emulate was done with software called
> Comprehensive Meta-analysis. The "ideal" graph is formatted something
> like below.
> --------------------------------------------------------------
> ----------
> -------------------
> Citation		    Effect   N total	-2.00    -1.00   0.00
> 1.00    2.00
> 
> Bones & Smith 1999	.203		26	   |  	|	 |
> ---*--|-	    |
> Jones 2003			.450	     235	   |	      |
> |--*--  |	    |
> ...
> --------------------------------------------------------------
> ----------
> -------------------
> 
> Thanks in advance for advice as to what SE or forest plot is the most
> customizable. 

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index