Surv {bayesCureRateModel} | R Documentation |
Create a Survival Object
Description
Create a survival object for use in survival analysis, as imported from the survival package.
Usage
Surv(time, time2, event, type = c("right", "left", "interval",
"counting", "interval2", "mstate"), origin = 0)
Arguments
time |
The follow-up time. For counting process data, this is the start time. |
time2 |
The end time for counting process or interval-censored data. Optional for right-censored data. |
event |
The event indicator, normally 0=alive/censored, 1=dead/event occurred. Can also be a factor or logical. |
type |
Type of censoring. Options are |
origin |
Starting point for time scale. Default is 0. Only used for type |
Details
The Surv
function creates an object of class "Surv"
, which is used to represent survival data. Depending on the arguments, the object can represent different types of censoring.
Right-censoring: one time and event indicator.
Left-censoring: similar to right-censoring but event=1 for censored.
Interval-censoring: requires both
time
andtime2
.Counting process: both
time
andtime2
used to specify start and stop times.
The resulting object is used as a response in survival regression models and estimation functions.
Value
An object of class "Surv"
which is used as a response in survival models.
Note
The implementation in the bayesCureRateModel package only supports right-censored data. The binary censoring indicators are interpreted as a time-to-event (1) or as a censoring time (0).
References
Therneau T (2024). A Package for Survival Analysis in R. R package version 3.7-0, https://CRAN.R-project.org/package=survival.
See Also
Examples
# Right-censored survival data
Surv(5, 1)
Surv(c(5, 10), c(1, 0))