Re: Clustering categorical data

Hi Jiana,

You say "categorical" data, but you also mention "5-point scales",
which suggests that you have ordered-categorical or else Likert-type
data, and probably the latter.

In this case my personal suggestion would be to treat the data as
interval-level measurement, and to perform some form of ordinary
cluster analysis, like k-means or hierarchical clustering.

The case for treating the data as interval-level is made stronger if
your "scales" are (1) internally symmetrical in wording, and (2)
accompanied by a visual analog scale with equally-spaced intervals.

So there is no confusion, your case is a little unusual in that your
objects/cases here are "items", which are measured on
"characteristics." Though you are clustering items, this is not a
cluster analysis of variables, but of objects. The possible confusion
develops because one may cluster either cases or variables, and the
latter is sometimes called "item cluster analysis." Here you are
clustering items, but it is a standard "object cluster analysis."

Hope this helps.

John Uebersax PhD
ourworld.compuserve.com/homepages/jsuebersax

On Feb 15, 11:25 pm, jiana <cannon.jan...@xxxxxxxxx> wrote:
I'm desparately trying to find a procedure to cluster categorical
data. I have 100 items, each rated on 12 characteristics. The
responses were collected on 5 point catagorical specific scales and
want to assemble the items into groups. Can you help? Any
suggestions?

.

Relevant Pages

  • Re: Finding useful functions- part 1
    ... Bear in mind that I actualy write cluster ... > The one thing one soon learns after using cluster analysis practically ... approach to the functional classification of neurons, ... cells can be clustered so that most of the diversity is captured by the ...
    (sci.cognitive)
  • Re: Cluster analysis
    ... I am working as a tec consultant for Statistica ... having two methods of cluster analysis: ... you can go for k-means clustering method ... Cluster Analysis.Both of these tools can be used for cluster analysis. ...
    (sci.stat.consult)
  • Re: clustering
    ... > going from a five cluster step to a 4 cluster step, ... into the subject of "cluster analysis" about a DECADE after I ... ALL existing clustering algorithms! ... In Art' second sentence, it is imperative to drop the word "easily". ...
    (sci.stat.edu)
  • Re: Cluster analysis on dataset with ordinal and nominal data
    ... The TWOSTEP cluster procedure in SPSS handles variables at different ... If you are using Likert scales, ... > 2) Is there any alternative method of cluster analysis of this dataset ...
    (sci.stat.edu)