Togaware DATA MINING
Desktop Survival Guide
by Graham Williams
Google

Simple

The simple dataset consists of just 10 data points with 1 covariate (predictor) called x:



> simple <- data.frame(time=c(1, 2, 3, 5, 7, 11, 4, 6, 9, 10),
                       status=c(0, 1, 0, 0, 1, 0, 0, 0, 1, 1),
                       age=c(50, 70, 45, 35, 62, 50, 45, 57, 57, 60))
> simple



   time status age
1     1      0  50
2     2      1  70
3     3      0  45
4     5      0  35
5     7      1  62
6    11      0  50
7     4      0  45
8     6      0  57
9     9      1  57
10   10      1  60

First we create a so-called survival object which takes the time and status variables and constructs an object which essentially summarises the censoring. Such an object is used as a response variable in a model formula. The event variable (status) is normally 0/1 or FALSE/TRUE or 1/2, representing alive/dead respectively.



> library(survival)
> s.Surv <- Surv(simple$time, simple$status)
> s.Surv



 [1]  1+  2   3+  5+  7  11+  4+  6+  9  10

Notice that those with a + correspond to times at which the observed event of interest (the 1) has yet to occur. The + means still alive.



Copyright © 2004-2010 Togaware Pty Ltd
Support further development through the purchase of the PDF version of the book.
The PDF version is a formatted comprehensive draft book (with over 800 pages).
Brought to you by Togaware. This page generated: Sunday, 22 August 2010