R help - Aug 2012 - choosing the correct number of clusters usinf NbClust

I am attempting to use NbClust to examine different indices to determine
the number of clusters.  The code appears to be working and I am getting
results.  However, I have noticed that each time I run it I may get
different answers.  For example looking at the DB index one run
recommended 6 clusters while the next 5 - the code is exactly the same.
I assume there is some randomization that I don't see.  Is there a way
to get a consistent answer. Thanks.

-Lisa
	[[alternative HTML version deleted]]