Statalist


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

RE: st: How to - scatter plot with regression line after adjustment for covariates


From   "Hoffman, George" <ghoffman@mcw.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: How to - scatter plot with regression line after adjustment for covariates
Date   Tue, 11 Mar 2008 06:21:38 -0500

You might want to look at predxcon.ado, by joanne garrett. It predicts y by x (regression) and allows covariates for adjustment. 
You could also manually predict y and se after your adjusted regression, and draw the regression line with ci's on top of the scatterplot. Consult the online regression faqs.

 george hoffman

-----Original Message-----
From: "roland andersson" <rolandersson@gmail.com>
To: "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Sent: 3/11/2008 05:18 AM
Subject: st: How to - scatter plot with regression line after adjustment for covariates

I am helping a colleague that wants to describe the relation between
vascular wall stiffnes and wall tension for 30 patients. In a simple
linear regression analysis the association is almost significant, but
the scatterplot does not show the association so clear. The points are
very scattered around the regression line.

After adjustment for age and sex the relation becomes strongly
significant. I would like to make a scatterplot with added regression
lines of the association after adjustment for age and sex. I guess I
can use confidence limits to illustrate the strong association, but is
it also possible to show the points after adjustment?

Regards
Roland
*
*   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/

*
*   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