[R] tool for cluster analysis

[David L Carlson]

First, you are using a very old version of R. The current version is 2.15.2. The version you are using was released in summer 2005 so you should upgrade as soon as possible. 

Second, there are many tools available for cluster analysis. You should tell us exactly what you trying to do, not give us examples of the kind of thing you want. You are confused by the dendrogram and ask for a matrix with different numbers for each group. That suggests you may not understand how hierarchical clustering works. The program (agnes() in cluster or hclus() in base R) begins with as many clusters as observations and then combines observations or clusters at each stage until there is only one cluster. The entire process is displayed in the dendrogram.

To get cluster assignments, you need to specify where the clustering process should stop and then use the cutree() function to give you the cluster assignments at that stage (?cutree to get the help page).

----------------------------------------------
David L Carlson
Associate Professor of Anthropology
Texas A&M University
College Station, TX 77843-4352



> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of rajashekar
> Sent: Thursday, December 06, 2012 8:01 AM
> To: r-help at r-project.org
> Subject: [R] tool for cluster analysis
> 
> I have Windows XP Professional Version 2002 and the R-Version 2.1.1.
> I did cluster analysis with the cluster package and the agnes (method =
> “ward”).
> The results are satisfactory.
> But the dendrogram of agnes is confused to work with the results.
> Is there a tool, I can get a clear arrangement of the results for the
> cluster analysis.
> For example a matrix with different numbers for each group.
> 
> 
> 
> 
> 
> 
> 
> -----
> 
> 
> 
> 
> --
> View this message in context: http://r.789695.n4.nabble.com/tool-for-
> cluster-analysis-tp4652333.html
> Sent from the R help mailing list archive at Nabble.com.
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.