Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: -hcavar- "too many leaves"


From   Mark Taylor <mark.taylor-3@manchester.ac.uk>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: -hcavar- "too many leaves"
Date   Mon, 28 Oct 2013 10:22:13 +0000

Dear Statalist

Using Stata 13.0 for Mac, I'm using the user-written command -hcavar-. This command's available at http://ideas.repec.org/c/boc/bocode/s439403.html, and the details on my machine are as follows

*! Version 3.2 15 April 2010

*! Jean-Benoit Hardouin

I'm using this command for hierarchical cluster analysis on a large number of variables, along the lines of

********************************************

hcavar var1 var2 var3... var99,partition(1/30)

********************************************

However, when I exceed 100 variables, I get the following output

********************************************

--------------------------------------------------------------------------------

Number of individuals with none missing values: 71577

Maximal number of modalities for a variable: 9

Proximity measures: Pearson

Method to aggregate clusters: Unweighted Pair-Group Method of Average

--------------------------------------------------------------------------------

too many leaves; consider using the cutvalue() or cutnumber() options

r(198);

********************************************

In Googling this error message (such as at http://www.stata.com/statalist/archive/2008-03/msg00685.html), it seems  that this error comes because the dendogram can't handle that many leaves - but I can't figure out how to turn off the dendogram. The help file says that {cmdnodendogram} enables the displaying of the dendogram, but typing -nodendogram-  tells me that option isn't allowed. (There are other methods to aggregate clusters which don't have this problem, such as -median-, but these aren't as useful for me.)

Any advice would be gratefully received.

Mark
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index