R help - Nov 2010 - How to represent factor levels & ordiellipses using different colors?

Dear Jari Oksanen,

I am Trinadh Kumar, a student of Biotechnology from Texas Tech University.
I have a question for you regarding constrained ordination graphs.
I had previously plotted constrained ordination graphs using distance based
redundancy analysis for species data on patients.
The species matrix consists  of 70  patients and 274 species of bacteria.The
metadata matrix consists of 10 variables(environmental matrix)
My Professor asked me to do the following.To plot a constrained ordination
plot constrained by tobacco habit(which is one of the factors). However he
asked me to represent  the graph as follows..
Represent the significant species (species that are farthest from the origin
in the direction of  the environmental variable) with biplot arrows pointing
from origin to the species and hide the insignificant species(closer to the
origin) on  the graph. Also he asked me to use colored solid circles for
plotting patients(instead of patient names) with the three levels of the
tobacco factor( for example: red circle to represent tobacco0, green circles
to represent tobacco1, black circles to represent tobacco2).He asked me to
shade the 95% confidence ellipses with the same color as the levels of
tobacco factor.

Please advice.


Thanks,

Trinadh

	[[alternative HTML version deleted]]