[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: Cluster dendrogram

From   "Nick Cox" <>
To   <>
Subject   RE: st: Cluster dendrogram
Date   Thu, 20 Mar 2008 15:36:28 -0000

I don't think that would have any effect upon Mike's problem. 
The issue is drawing a graph of the clustering. How do you do 
the clustering is immaterial to that. 


Joao Ricardo F. Lima

why donīt you use kmeans? Nonherarchical methods can be applied to
much larger data sets than hierarchical techniques.

2008/3/18, Davis Mike <>:

> I have a question about Cluster dendrogram.
> Now, I am using the cluster analisis as follows.
> cluster ward var1 var2 var...., measure(matching) name(cluster)
> After that, I try "cluster dendrogram cluster" as the postclustering.
> However, error message "too many leaves; consider using the cutvalue()
> or cutnumber() options" appears.
> When there are many observations, the dendrogram would become too crowded.
> However, I would not like to limit the dendrogram.
> Would you please teach me how to remove the limit of the dendrogram?

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index