R help - Aug 2003 - cluster analysis

I'like to do cluster analysis by using mahalanobis distance.
Could you tell me how to do?

On Mon, 11 Aug 2003, HIRAOKA Yuichiro wrote:
> I'like to do cluster analysis by using mahalanobis distance.
> Could you tell me how to do?
Could you tell us more precisely what you want?

"cluster analysis by using mahalanobis distance" could mean:
1) Compute Mahalanobis distances (command mahalanobis)
   and then apply any distance based cluster method (which?)
2) Fit normal mixture with unrestricted covariance matrix: use model 
   "VVV", command EMclust (library mclust)
3) Do Mahalanobis fixed point cluster analysis with command fixmahal
   (not too well known up to now, but it's a nice method in my package fpc)
4) Something else?

Best,
Christian

-- 
***********************************************************************
Christian Hennig
Seminar fuer Statistik, ETH-Zentrum (LEO), CH-8092 Zuerich (currently)
and Fachbereich Mathematik-SPST/ZMS, Universitaet Hamburg
hennig at stat.math.ethz.ch, http://stat.ethz.ch/~hennig/
hennig at math.uni-hamburg.de, http://www.math.uni-hamburg.de/home/hennig/
#######################################################################
ich empfehle www.boag.de

Mahalonobis distance depends on having models for the "clusters"
sharing a
common dispersion structure. Are you sure that you mean cluster analysis
and not discriminant analysis. That is, do you have a "training
sample"
that is already classified into classes?

Murray Jorgensen

At 17:37 11/08/2003 +0900, HIRAOKA Yuichiro wrote:
>I'like to do cluster analysis by using mahalanobis distance.
>Could you tell me how to do?
>
>______________________________________________
>R-help at stat.math.ethz.ch mailing list
>https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> 
Dr Murray Jorgensen      http://www.stats.waikato.ac.nz/Staff/maj.html
Department of Statistics, University of Waikato, Hamilton, New Zealand
Email: maj at waikato.ac.nz                                Fax 7 838 4155
Phone  +64 7 838 4773 wk    +64 7 849 6486 home    Mobile 021 1395 862