Survival Analysis

This course provides an introduction to the statistical methods used for analyzing time-to-event data. Time-to-event data can be found in various settings, e.g. time until death, recurrence of a tumor or discharge from a hospital. You will learn the theory and practice of survival analysis, a critical tool for studies where the outcome of interest is the time until an event occurs, such as patient survival or equipment failure. The course focuses on the practical implementation of key techniques, from non-parametric survival curves to regression-based modeling, using the R programming language.

Target Audience

Researchers who work with longitudinal or time-to-event data and need to learn the standard methods for survival analysis.

Topics

This course on survival analysis covers four parts:

• Foundations of Survival Analysis:
  • Understanding time-to-event data and the concept of censoring.
  • Defining and interpreting survival and hazard functions.
• Non-Parametric Methods:
  • Estimating and visualizing survival curves using the Kaplan-Meier method.
  • Comparing survival distributions between groups (e.g., with the log-rank test).
• Cox Proportional Hazards Model:
  • Building and interpreting semi-parametric regression models.
  • Assessing model assumptions and selecting variables.
• Parametric Survival Models:
  • Applying parametric models like the Weibull regression as an alternative.
  • Contrasting parametric and semi-parametric approaches.

Methods

Each module introduces a concept, which is then immediately applied in practical coding exercises with best-practice solutions.

Learning Goals

At the end of this course, you will be able to:

1. Identify and correctly structure time-to-event data, accounting for censoring.
2. Create, visualize, and interpret Kaplan-Meier survival curves to describe survival patterns.
3. Compare survival distributions between two or more groups using appropriate statistical tests.
4. Build, interpret, and critically evaluate Cox proportional hazards regression models.
5. Implement a complete survival analysis workflow in R, from data exploration to modeling.

Prerequisites

Programming skills in R (e.g., Introduction to R) and a basic knowledge of regression models and hypothesis testing (e.g., from Introduction to Statistics).

Format

• Duration: either 2 full days or 4 half days
• Language: English
• This course will be offered either on campus (in person), or online
• For online courses we use the software Zoom.

Dates and Application

• Courses provided for Helmholtz Munich:
  • You can check the current dates and whether the courses are already fully booked here*.
  • Please read the corresponding FAQ* before applying via the forms of the HR Development department*.

 * Links marked with * are only available for Helmholtz Munich staff.