Statalist


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

st: RE: classification & regression trees


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: classification & regression trees
Date   Tue, 16 Dec 2008 17:46:35 -0000

Official Stata has no implementation of CART. 

There is no user implementation in Stata of CART that I know of that stands comparison with any in other substantial statistical programs. 
The -cart- that you mention is surely misnamed, as it is much more specific than one would expect from that name alone. 

In terms of you can do now, you should look outside Stata if you want CART. 

That said, if you ever seriously considered factor analysis as an alternative to CART, it does not seem to me that your problem is pre-defined as a CART problem. 

I don't know what "mediation analyses" are in this context, or indeed any other. 

I think it's fair to say that StataCorp or its predecessor company have never seen the mission of Stata as including every serious statistical method. No doubt many users would like that, but I don't think it's intended, or practical. Still, StataCorp can speak for itself, or not. 

(At some users' meeting I attended, the rhetorical question "You wouldn't want to do everything, such as say your word processing, in Stata, would you?" got "Oh yes, please" as a fervent response from several users.) 

Nick 
n.j.cox@durham.ac.uk 

Elizabeth Mumford

As of April 2007, according to the archives, Stata was still thinking
about whether to add a CART-like classification tree program to the
package.  I downloaded the "cart" module that addresses failure time
analyses, but I don't think that will meet my needs (or maybe I am not
understanding its potential).  Are there other options I am missing?  My
task is to examine individual strategies (20) within an overall
intervention to try to determine the mechanism by which the intervention
is effective.  (Factor analyses and mediation analyses are not shedding
much light on the question, and a colleague suggested SPSS’s CART.)


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



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index