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

Re: st: ci question

From   Chris Witte <>
Subject   Re: st: ci question
Date   Thu, 10 Apr 2008 14:17:54 -0700 (PDT)

Regarding the second question of my original message:

I'd like to be able to have multiple levels by which the plots are separated/grouped along the x-axis (like the "over" command in "graph box" allows).  For example, using eclplots, I'd like to be able to include two "parmid_varname" variables....or using ciplots, I'd like to include two variables in the "by" option.  

Now, I've also plotted this data by overlaying rcap plots with scatter plots of the means.  Using this plotting method, is there a way to horizontally offset the rcap plots within a single x-axis value so that the rcaps do not overlap?  This might be an acceptable presentation for me as well, although it would be better if I could do this through ciplot, eclplot, or serrbar.


----- Original Message ----
From: Nick Cox <>
Sent: Thursday, April 10, 2008 2:31:33 PM
Subject: RE: st: ci question

Also note -ciplot- from SSC.  

David gave a very interesting reference new to me. Thanks for that. In
W.S. Cleveland. 1994. The elements of graphing data. Summit, NJ: Hobart
is good on graphing error bars. 

David Airey

also see ecloplot for an estimate and confidence limits plot for an  

findit eclplot finds it for you inside stata...

also see a recent paper on different error bars that might be used...

The Journal of Cell Biology, Vol. 177, No. 1, April 9, 2007 7-11

Email me if you don't have access to the paper.

If you really want the means and standard errors you can collapse the  
data set to to means, sd, and counts, derive the sems, and then plot  
means and sems with a scatter and rcap plot combined in a twoway graph.


On Apr 10, 2008, at 2:04 PM, Chris Witte wrote:
> I would like to know how to take the means and standard errors  
> calculated from the "ci" command, and plot the means with brackets  
> placed at plus/minus the standard error.
> 1) So, I first need to know how to get these estimates into a  
> dataset for use.
> 2) I found the "serrbar" command, which will do a basic plotting,  
> but what I'd really like is to have a way to group these estimates,  
> much like the way you can with "graph box" and the "over" option.  
> Is this possible?

*  For searches and help try:

Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index