[R] biplot breakdown help

[chris20]

Hi,
I am trying to understand how the biplot.prcomp is constructed so I can
manipulate it to emphasise particular observations and reduce the number of
variables shown.

The prcomp model I have ran has cor=TRUE and scale=TRUE

I have worked out from looking at str(prcomp.model) that...

prcomp.model$x = the observations ploted in the biplot

prcomp.model$rotation = the variables that form the arrows.

But there appears to be a scaling factor because when I plot 
biplot(prcomp.model$rotation, prcomp.model$x)
The biplot is slightly off scale compared with biplot(prcomp.model)

Under ?biplot.prcomp it talks about lambda^scale and lambda^(1-scale) but I
just can't seem to work it out so that the two biplots look the same. HELP!!

Thanks
Chris 



--
View this message in context: http://r.789695.n4.nabble.com/biplot-breakdown-help-tp3344458p3344458.html
Sent from the R help mailing list archive at Nabble.com.