Event times and event counts appear in many social and medical data contexts, and require a specialised suite of techniques to handle properly, broadly known as survival analysis. This course covers the basic definitions and techniques for creating life tables, estimating event-time distributions, com-paring and testing distributions of different populations, and evaluating the goodness of fit of various models. A focus is on understanding when and why particular models ought to be chosen, and on using the standard software tools in R to carry out data analysis.

Key Themes

  • Life tables
  • Kinds of event-time data: Censoring and truncation
  • Non-parametric and semi-parametric survival models
  • Model diagnostics for survival models

Learning Objectives

At the end of this course students will…

  • Understand the standard notation of life tables, and be able to make inferences from life tables
  • Interpret censored and truncated data
  • Derive estimators and confidence intervals for standard parametric survival models
  • Fit survival curves with standard non-parametric techniques using R, and interpret the results.
  • Select appropriate tests for equality of survival distributions, and carry out the tests in R.
  • Fit semi-parametric survival models in R and interpret the results.
  • Estimate the goodness of fit of survival models using graphical and residual techniques.
  • Make individual predictions based on survival data.

Topics

  1. Introduction to survival data: hazard rates, survival curves, life tables.
  2. Censoring and truncation, introduction through the census approximation.
  3. Parametric survival models
  4. Non-parametric estimation of survival curves
  5. Non-parametric model tests (log-rank test and relatives)
  6. Semi-parametric models
  7. Model-fit diagnostics
  8. Dynamic prediction and model information quality
  9. Repeated events
This page was last modified on 3 October 2018