Skip to content

Chapter 1: What is Survival Analysis?

install.packages("TH.data")
# Packages
library(tidyverse)
library(TH.data)
Hidden output
  • We are interested in the time until the event occurs. For example:
    • Time until death
    • Time until the cab takes you after you call it
    • Time until you get a new job after you get unemployed, and so on
# Datasets we are going to use
data(GBSG2, package = "TH.data")

Taking a look at the data

# Check out the help page for this dataset
help(GBSG2, package = "TH.data")

# Load the data
data(GBSG2, package = "TH.data")

# Look at the summary of the dataset
summary(GBSG2)

Creating Surv objects

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

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

Digging into GBSG2 dataset

# Our data set is called GBSG2 and is from package TH.data
data("GBSG2", package = "TH.data")

# Count censored and uncensored data
num_cens <- table(GBSG2$cens)
num_cens

# Create barplot of censored and uncensored data
barplot(num_cens)

# Use help() to look at cens
help(GBSG2, package = "TH.data")

Using the Surv() function for GBSG2

# Create Surv-Object
sobj <- Surv(GBSG2$time, GBSG2$cens)

# Look at 10 first elements
sobj[1:10]

# Look at summary
summary(sobj)

# Look at structure
str(sobj)

The UnempDur dataset

  • The UnempDur dataset contains information on how long people stay unemployed.
‌
‌
‌