K-modes clustering was originally developed by Anil Chaturvedi, Paul Green and me in 1994, but, for various reasons, not published until 2001.  K-modes indeed is the optimal procedure to use for the problem of clustering categorical data you describe.  The reference for our paper is:

Chaturvedi, A.D.,  Green, P.E. & Carroll, J.D. (2001).  K-modes clustering.  Journal of Classification, 18, 35-56.

Doug Carroll

At 09:39 AM 2/4/2008, Arnaud Trollé wrote:

Hello,
 
I'd like to cluster categorical data (3 categories) by means of a partitioning
method; I'm quite a beginner in that field and I would need to be enlightened.
From a bibliographic review I carried out about that topic, it appeared to me
that a method is often used :the k-modes method. From her/his experience,
could anyone confirm or deny that it is the case ? If denied, which method
could be more "powerful" ?

Thanks in advance.

Best Regards.
Arnaud.
PhD Student in Acoustics.
Lyon, France.

----------------------------------------------
CLASS-L list.
Instructions: http://www.classification-society.org/csna/lists.html#class-l

  ######################################################################
  # J. Douglas Carroll, Board of Governors Professor of Management and #
  #Psychology, Rutgers University, Graduate School of Management,      #
  #Marketing Dept., MEC125, 111 Washington Street, Newark, New Jersey  #
  #07102-3027.  Tel.: (973) 353-5814, Fax: (973) 353-5376.             #   
  # Home: 14 Forest Drive, Warren, New Jersey 07059-5802.              #   
  # Home Phone: (908) 753-6441 or 753-1620, Home Fax: (908) 757-1086.  #   
  # E-mail: [log in to unmask]                                   #
  ###################################################################### ---------------------------------------------- CLASS-L list. Instructions: http://www.classification-society.org/csna/lists.html#class-l