rmst: Restricted Mean Survival Times.

In RISCA: Causal Inference and Prediction in Cohort-Based Analyses

Restricted Mean Survival Times.

Description

This function allows to estimate the Restricted Mean Survival Times (RMST).

Usage

rmst(times, surv.rates, max.time, type) 

Arguments

times	A numeric vector with the times.
surv.rates	A numeric vector with the survival rates.
max.time	The maximum follow-up time.
type	The type of input survival cirves. Two possible arguments: "s" for a step function or "l" for a continous function.

Details

RMST represents an interesting alternative to the hazard ratio in order to estimate the effect of an exposure. The RMST is the mean survival time in the population followed up to max.time. It corresponds to the area under the survival curve up to max.time.

References

Royston and Parmar. Restricted mean survival time: an alternative to the hazard ratio for the design and analysis of randomized trials with a time-to-event outcome. BMC Medical Research Methodology 2013;13:152. <doi: 10.1186/ 1471-2288-13-152>.

Examples

data(dataDIVAT2)

#Survival according to the donor status (ECD versus SCD)
res <- summary(survfit(Surv(times,failures) ~ ecd, data=dataDIVAT2))

#The mean survival time in ECD recipients followed-up to 10 years
rmst(times = res$time[as.character(res$strata)=="ecd=1"],
 surv.rates = res$surv[as.character(res$strata)=="ecd=1"],
 max.time = 10, type = "s")
 
#The mean survival time in SCD recipients followed-up to 10 years
rmst(times=res$time[as.character(res$strata)=="ecd=0"],
 surv.rates=res$surv[as.character(res$strata)=="ecd=0"],
 max.time=10, type = "s")

RISCA documentation built on March 31, 2023, 11:06 p.m.