In the first chapter, we introduce the concept of survival analysis, explain the importance of this topic, and provide a quick introduction to the theory behind survival curves. We discuss why special methods are needed when dealing with time-to-event data and introduce the concept of censoring. We also discuss how we describe the distribution of the elapsed time until an event.

The term "survival analysis"

Introducing the GBSG2 dataset

What will this course cover?

Why learn survival methods?

Digging into the GBSG2 dataset 1

Using the Surv() function for GBSG2

The UnempDur dataset

Measures used in survival analysis

Interpreting a survival curve I

Interpreting a survival curve II

Interpreting a survival curve III

What is Survival Analysis?

In this chapter, we will look into different methods of estimating survival curves. We will discuss the Kaplan-Meier estimate and the Weibull model as tools for survival curve estimation and learn how to communicate those results through visualization. 

Kaplan-Meier estimate

Function to compute the Kaplan-Meier estimate

First Kaplan-Meier estimate

When does the Kaplan-Meier curve drop?

Why use Kaplan-Meier

Understanding and visualizing Kaplan-Meier curves

Exercise ignoring censoring

Estimating and visualizing a survival curve

The Weibull model for estimating survival curves

Estimating median survival from a Weibull model

Survival curve quantiles from a Weibull model

Estimating the survival curve with survreg()

Visualizing the results of Weibull models

Comparing Weibull model and Kaplan-Meier estimate

Estimation of survival curves

In this chapter, we will learn how to estimate and visualize a Weibull model to learn about the effects of covariates on the time-to-event outcome.

Why use the Weibull model

Interpreting coefficients

Compute Weibull model

Visualizing Weibull models

ggsurvplot() versus ggsurvplot_df()

Computing a Weibull model and the survival curves

Visualising a Weibull model

Plotting options

Other distributions than Weibull

survreg() arguments

Computing a Weibull and a log-normal model

Comparing Weibull and Log-Normal Model I

Comparing Weibull and Log-Normal Model II

The Weibull model

In the last chapter, we learn how to compute and interpret Cox models to understand why they are useful and how they differ from Weibull models.

The Cox model

Computing a Cox model

Proportional hazards assumption

Visualizing the Cox model

Computing the survival curve from a Cox model

Visualizing a Cox model

surv_summary()

What we've learned

Why "imaginary patients"?

Capstone: The Cox model

Capstone: Comparing survival curves

Good bye

The Cox Model

Do patients taking the new drug survive longer than others? How fast do people get a new job after getting unemployed? What can I do to make my friends stay on the dancefloor at my party? All these questions require the analysis of time-to-event data, for which we use special statistical methods. This course introduces basic concepts of time-to-event data analysis, also called survival analysis. Learn how to deal with time-to-event data and how to compute, visualize and interpret survivor curves as well as Weibull and Cox models.

Introduction to Regression in R

Learn to work with time-to-event data. The event may be death or finding a job after unemployment. Learn to estimate, visualize, and interpret survival models!

Survival Analysis in R

Statistiker in R

ggsurvplot() versus ggsurvplot_df()

Survival Analysis in R

Interaktive Übung