wwreith
2012-May-03 12:57 UTC
[R] Creating a survival object with and without an event indicator
When reading about surv(). I saw the following statement "Although unusual, the event indicator can be omitted, in which case all subjects are assumed to have an event." So I tried the following 1. survobj<-surv(mydata$Time) vs. 2. survobj<-surv(mydata$Time, mydata$Event) where mydata$Event is a column of all ones. I did not get the same answer when I ran survreg(survobj~shift, data=mydata) on each. The second case actually failed to converge. I then tried a column of all zeros just to make sure I wasn't misreading something but still got the warning message failed to converge. Can anyone explain what exactly R is doing for case 1? -- View this message in context: http://r.789695.n4.nabble.com/Creating-a-survival-object-with-and-without-an-event-indicator-tp4605945.html Sent from the R help mailing list archive at Nabble.com.