s-news
[Top] [All Lists]

a question on using RPART library

To: <s-news@wubios.wustl.edu>
Subject: a question on using RPART library
From: "Feng Gao" <feng@wubios.wustl.edu>
Date: Tue, 17 Jan 2006 16:24:33 -0600
Importance: Normal

Dear S users:

 

I ran into a minor question recently when I used RPART library (http://www.stats.ox.ac.uk/pub/S/S+6/) to develop survival trees. My Splus is version 6.2 based on Linux.

 

My understanding is that the “where” variable in the fitted model should contain the #code of the terminal nodes, but it does not (see below). Did I miss anything in the documentation? Many thanks!    

 

> fit2<-rpart(Surv(t, cen)~……, data="" cp=0.01)

>  print(fit2)

 1) root 1309 956.22140 1.0000000 

   2) c>=554.35 956 495.65270 0.6112466 

     4) g< 54.5 438 151.44680 0.3263974 

       8) d< 0.6375 414 111.40080 0.2362070 *

       9) d>=0.6375 24  26.99685 1.6767380 *

     5) g>=54.5 518 327.74550 0.8840053 

      10) d< 0.2975 189  70.41894 0.4046790 *

      11) d>=0.2975 329 244.85950 1.1946230 *

   3) c< 554.35 353 401.67170 2.0416440 

     6) p< 27.65625 312 316.47580 1.7135160 

      12) c>=506.4 277 247.53830 1.4669180 *

      13) c< 506.4 35  59.02539 3.5131440 *

     7) p>=27.65625 41  71.36904 4.0764780 *

 

> sort(unique(fit2$where))

[1]  4  5  7  8 11 12 13

>

Feng Gao, Ph.D.
Division of Biostatistics,
Washington University School of Medicine
Campus
Box 8067, 660 S. Euclid Av.
St. Louis, MO 63110-1093
Phone: 314-362-3682
Fax:     314-362-3728

The materials contained in this e-mail are private and confidential and are the property of the sender.  If you are not the intended recipient, be advised that any unauthorized use, disclosure, copying, distribution, or the taking of any action in reliance on the contents of this information is strictly prohibited.  If you have received this e-mail transmission in error, please immediately notify the sender.

<Prev in Thread] Current Thread [Next in Thread>
  • a question on using RPART library, Feng Gao <=