[R] Re: model-based clustering

[Christian Hennig]

Dear Talita,

you may start with
library(mclust)
?EMclust
example(EMclust)
# The example is with Iris data.

To understand what you're doing, read a paper from the web page
of the developers, cited on the help page.

Best,
Christian

PS: What a "good" or "optimal" clustering is, is by no means well defined.
    Some cluster algorithms will find 2 or more than 3 clusters on Iris,
    and that's not necessarily an argument against these algorithms.
 
On Tue, 13 Apr 2004, Talita Leite wrote:

> Hello again,
> 
> Let me explain this better. I've been working in clustering methods during 
> this year and now i'm starting (or trying to) with model-based clustering. 
> I've been searching for help to understand how the functions works and i 
> found some. The problem is that i don't know the steps to follow. For 
> example: working with the data set IRIS. What steps do i have to follow and 
> what functions do i have to use to make a good clustering? To find the three 
> groups on that case?
> 
> Thanks,
> 
> Talita
> 
> _________________________________________________________________
> 

***********************************************************************
Christian Hennig
Fachbereich Mathematik-SPST/ZMS, Universitaet Hamburg
hennig at math.uni-hamburg.de, http://www.math.uni-hamburg.de/home/hennig/
#######################################################################
ich empfehle www.boag-online.de