Statalist The Stata Listserver


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

RE: st: Regression tree (CART analysis)


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Regression tree (CART analysis)
Date   Thu, 19 Oct 2006 21:41:38 +0100

There is indeed a version for R somewhere. I think it is discussed
briefly in Venables and Ripley's book. Without having used
either I guess that the commercial CART has more bells 
and whistles, but otherwise the R version is distinctly
(even infinitely) cheaper. 

I guess a general Stata version is unlikely in finite time. CART 
is manifestly not trivial, while at the same time I sense that -- for 
slightly different reasons -- that both Stata developers 
and user-programmers have little interest in devoting the time 
to writing an implementation, especially given the R implementation. 
Naturally, one counter-example would smash this guess. 

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

Fred Wolfe
 
> In the 1980s and early 1990s the CART program (Salford Systems) was 
> relatively inexpensive. Recently (when I last looked several 
> years ago) its 
> price was in the thousands of dollars and the license was not 
> perpetual. 
> It's marketed as "data mining" to corporate users.
> 
> S-Plus has a Cart program and a presume that the free R also has it.
 
> >I am trying to do a CART-type analysis, but the only
> >relevant package I have found, van Putten's -cart-
> >package, is of no use for me.
> >Are there any other cart packages available for stata?
> >If not, would the people who has done this type of
> >analysis please point in the direction of the
> >statistical software they used?

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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