R help - May 2011 - help: Using hotelling for a confidence region for PCA scores

Hello everyone.

 In my last post I did not explained my problem quite well. I made a principal
component analysis and took the 2 first principal components. I made ​​a chart
of my points based on the score of the 2 PC. I would like to add on this graph a
95% confidence region. To do this I used the ellipse function as follows:


pcsref=PC$score[data[,1]==ref,1:2]  #matrix containing the scores of the two PC
SD=cov(pcsref[,1:2]) #covariance matrice of the two PC scores
lines (ellipse(SD, centre=colMeans(pcsref), level=0.95),type="l",
lty=5)

But I want the confidence region calculated by the Hotelling T2 method and
I'm not sure that ellipse function does it. Does anyone know how to do this?

 Thank you very much for your help and sorry for my english.
 		 	   		  
	[[alternative HTML version deleted]]

Jessica,

Take a look at the FactoMineR and SensoMineR packages:
http://cran.r-project.org/web/packages/FactoMineR/
http://cran.r-project.org/web/packages/SensoMineR/

Best,
Greg

On 5/16/11 2:14 AM, Jessica Minkue wrote:
> Hello everyone.
>
>  In my last post I did not explained my problem quite well. I made a
principal component analysis and took the 2 first principal components. I made
âEUR<âEUR
>
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
-- 
Greg Hirson
ghirson@ucdavis.edu

Graduate Student
Agricultural and Environmental Chemistry

1106 Robert Mondavi Institute North
One Shields Avenue
Davis, CA 95616


	[[alternative HTML version deleted]]