Biostatistics III: Introduction to Survival Analysis

Course Number       : KUI-7013
Credit points             : 2 (5 ECTS)
Censored time-to-event data, where not all subjects experience the event of interest, are common in clinical and cancer-epidemiologic research. Examples include randomized controlled trials of therapies for cancer and other chronic diseases, comparative effectiveness research, prognostic factor for cancer patients, and epidemiologic cohort studies. This lecture provides an introduction to censored time-to-event data and classical survival data analysis for the clinical and public health researchers.

In this lecture, we will provide examples of studies where survival analysis is used and when it should not be used.  We will describe how incomplete data on time-to-event outcomes (censoring) occurs.   We will introduce important functions, including the survival function,
the hazard function, and the median survival time, and show how censored data can be used to estimate them and compare the time-to-event experience between groups. The lecture module will explain key concepts unique to survival analysis such as risk sets and informative censoring. It will introduce the Cox regression model, show how to examine the proportional hazards assumption, and the interpretation of hazard rate (RR). The course will focus on application and understanding the concepts with examples from the biomedical literature; mathematical details will be kept to a minimum.

Aim

The course aims to introduce biostatistical concepts and methods for analyzing time-to-event data with emphasis on applications of clinical trials and cancer epidemiology.  

Learning outcomes

After successfully completing this course students should be able to:

1. explain a suitable statistical model for assessing a specific research hypothesis using data from clinical and cancer epidemiology research, fit the model using standard statistical software (stata or R), evaluate the fit of the model, and interpret the results,
2. explain central concepts in survival analysis: censoring, truncation, survivor function, and hazard function,
3. demonstrate how to calculate estimate of survival coefficient (or cumulative incidence and hazard) using non-parametric method (Kaplan Meier graph).
4. construct non-parametric method for testing differences in survival between groups (log rank),
5. estimate rates and modelling them using Poisson regression,
6. assess effect modification and confounding when modelling rates,
7. construct model for rates using Cox proportional hazards model,
8. assess the proportional hazards assumption,

Contents

This course introduces statistical methods for survival analysis with emphasis on the application of clinical trial and cancer epidemiology research. Topics covered include methods for estimating survival (life table and Kaplan-Meier methods), comparing survival between subgroups (log-rank test), and modelling survival (primarily Poisson regression and the Cox proportional hazards model). The course addresses the concept of 'time' as a potential confounder or effect modifier and approaches to defining 'time' (e.g., time since entry, attained age, calendar time). The course will emphasize the basic concepts of statistical modelling, such as controlling for confounding and assessing effect modification (interaction).

Literature and other teaching material

Recommended texts

• David G. K and Mitchel, K, Survival Analysis: A Self-Learning Text, 3^rd. 2012
• Machin, David ; Cheung, Yin Bun;  Parmar, Mahesh. Survival Analysis: A Practical Approach, 2nd Edition. 2006
• Cleves M et al. An Introduction to Survival Analysis Using Stata, 3rd edition. College Station: Stata Press; 2016.
• Breslow NE, Day NE. Statistical Methods in Cancer Research: The Design and Analysis of Cohort Studies. Lyon: IARC Scientific Publication; 1993.

Course director

Siswanto Agus Wilopo,

Professor of Department of Biostatistics, Epidemiology and Population Health, Faculty of Medicine, Public Health and Nursing, Universitas Gadjah Mada, Yogyakarta

and

Adjunct Full Professor of College of Health and Agricultural Sciences University College Dublin, Befield, Ireland.