Why do we need special methods for time-to-event data?

Survival Analysis in R

Heidi Seibold

Statistician at LMU Munich

Why survival analysis

Times are always positive
Different measures are of interest
Censoring almost always an issue

Why survival analysis

Times are always positive
Different measures are of interest
Censoring almost always an issue

Why survival analysis

Times are always positive
Different measures are of interest
Censoring almost always an issue

Creating Surv objects

time <- c(5, 6, 2, 4, 4)
event <- c(1, 0, 0, 1, 1)

library("survival")
Surv(time, event)

R packages

For all kinds of analyses:

library("survival")

For pretty visualisations:

library("survminer")

For more, see CRAN Task View: Survival Analysis

Let's practice!

Survival Analysis in R

Preparing Video For Download...