Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

Survival not recognizing right censored data

I'm trying to run a survival analysis in R using the survival package. I have right-censored data only (time to event, then event "1" or censor "0"). I created a survival object using the Surv function. However, survdiff and coxph give errors, suggesting that they do not recognize it as right-censored data. Any advice?

> surv.dfs <- Surv(DaysFromTx,Event)
> surv.dfs
[1]   99:1  334:1 1024+  1341+   210+  1069+   890+  1242+   255+   228+   349+   300+   717+     2+   657+   995+   491+  1544+   265:1  440+   362:1  845+ 
[23]  669+  1176+   718+   768+  1171+  2276+  1152+   207+  1138+  1002+   942+   644+  1110+   179:1 1535+   841+   923+   904+   367:1  959+   746+  1256+ 
[45]   83:1  439:1   69+   449+   591+   983+   787+   704+   825+   747+    28+    41+   907+   181:1  371+   388+   166:1  702+   647+   944+   903+   797+ 
[67] 1095+   770:1 1118+    63:1 1762+  1662+   127:1  634+   312+   483+ 
> survdiff(surv.dfs ~ group)

Error in survdiff(surv.dfs ~ group) : Right censored data only

> coxph(surv.dfs ~ group)

Error in coxph(surv.dfs ~ group) : Cox model doesn't support "mright" survival data

like image 316
C.C. Avatar asked Feb 15 '17 07:02

C.C.


People also ask

What does censored data mean in survival analysis?

Censoring. Censoring is a form of missing data problem in which time to event is not observed for reasons such as termination of study before all recruited subjects have shown the event of interest or the subject has left the study prior to experiencing an event. Censoring is common in survival analysis.

What is right censored data?

Right censored data is data for items that have not yet failed. They are considered “still alive” as their failure time has not yet occurred, though it is expected to occur at some point in the future. For example, consider a fatigue test with 10 components under test.

What does right censored mean?

In general, an observation is said to be right censored if the person was alive at study termination or was lost to follow-up at any time during the study. By right censoring, it is meant that the survival time is only known to exceed a certain value.


1 Answers

is your Event of a factor class? it should be numeric or boolean. so if your Event classes are 0 or 1, try:

df$Event <- as.numeric(df$Event)
like image 80
simitpatel Avatar answered Sep 22 '22 05:09

simitpatel