R help - Apr 2008 - plotting muliple CI ellipses for EB estimates

I have empirical Bayes estimates for slopes and intercepts for a number of 
subjects and I would like to plot the slopes and intercepts with confidence 
ellipses. These ellipses would be based on the confidence intervals for the 
slope and intercepts (forming the major and minor axis of each ellipse), and 
the correlation in the slope and intercepts.  


The ellipse function in the car library looks like the way to go, the add= 
argument would allow me to over-plot.  There are three arguments that generate 
the ellipse.

center 
shape 
radius

Center would be the posterior means for the intercept and slopes.
shape would be the posterior covariance matrices (I think)

I don't know what I would use for the radius argument however. My guess
would
be the upper bound of a confidence interval for either the slope or the 
intercept, but this does not return sensible results. I guess I need to know 
more about the geometry of ellipse, but if anybody can provide any assistance, 
I would really appreciate it.


thanks!



-- 
********Note the new contact information*******

Samuel H. Field, Ph.D. 
Senior Research Investigator
CHERP/Division of Internal Medicine - University of Pennsylvania
Philadelphia VA Medical Center
3900 Woodland Ave (9 East)
Philadelphia, PA 19104
(215) 823-5800 EXT. 6155 (Office)
(215) 823-6330 (Fax)

Dear Samuel,

The radius reflect the desired coverage of the ellipse. You should be able
to use  radius <- sqrt(qchisq(.95, 2)), I think.

I hope this helps,
 John

--------------------------------
John Fox, Professor
Department of Sociology
McMaster University
Hamilton, Ontario, Canada L8S 4M4
905-525-9140x23604
socserv.mcmaster.ca/jfox
> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Sam Field
> Sent: April-13-08 11:47 AM
> To: r-help at r-project.org
> Subject: [R] plotting muliple CI ellipses for EB estimates
> 
> I have empirical Bayes estimates for slopes and intercepts for a number
> of
> subjects and I would like to plot the slopes and intercepts with
> confidence
> ellipses. These ellipses would be based on the confidence intervals for
> the
> slope and intercepts (forming the major and minor axis of each
> ellipse), and
> the correlation in the slope and intercepts.
> 
> 
> The ellipse function in the car library looks like the way to go, the
> add> argument would allow me to over-plot.  There are three arguments
that
> generate
> the ellipse.
> 
> center
> shape
> radius
> 
> Center would be the posterior means for the intercept and slopes.
> shape would be the posterior covariance matrices (I think)
> 
> I don't know what I would use for the radius argument however. My guess
> would
> be the upper bound of a confidence interval for either the slope or the
> intercept, but this does not return sensible results. I guess I need to
> know
> more about the geometry of ellipse, but if anybody can provide any
> assistance,
> I would really appreciate it.
> 
> 
> thanks!
> 
> 
> 
> --
> ********Note the new contact information*******
> 
> Samuel H. Field, Ph.D.
> Senior Research Investigator
> CHERP/Division of Internal Medicine - University of Pennsylvania
> Philadelphia VA Medical Center
> 3900 Woodland Ave (9 East)
> Philadelphia, PA 19104
> (215) 823-5800 EXT. 6155 (Office)
> (215) 823-6330 (Fax)
> 
> ______________________________________________
> R-help at r-project.org mailing list
> stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.