School of Social and Community Medicine

Research

• Centres and units
• Themes
• Projects

Teaching

• Undergraduate
• Postgraduate
• Short courses
  • Booking information
  • Fees
  • Course location
  • Accommodation information
  • Contact details

About us

• People
• News
• Seminars

Rates and survival analysis: poisson, cox and parametric survival models

Tutors

Dr Sue Ingle (course organiser), Dr Margaret May, Prof Jonathan Sterne, Prof Kate Tilling

How to book on this course

Duration

Three days

Dates

3 - 5 June 2013

Course fee

£600

Course aims and objectives

By the end of the course students should:

• understand the usual measures of disease occurrence and exposure effect in longitudinal studies;
• be able to use Stata to manage and manipulate person-time data, derive graphical displays appropriate for survival analysis, and interpret these;
• be able to analyse data using Poisson, Cox and parametric (eg Weibull) regression models;
• understand the links between these approaches;
• understand how to model time-varying covariates;
• be able to analyse survival data with competing outcomes;
• interpret the results of survival analyses as presented in the published literature.

Please note that "repeated measures" analyses, in which multiple events or measurements are recorded in the same person over time, are not covered in this course. This topic is covered in the "Analysis of repeated measures course".

Who the course is intended for

Participants should have a knowledge of regression analyses and their implementation in Stata of at least the level achieved in the "Linear and Logistic Regression Models" short course. Familiarity with Stata is a pre-requisite for this course.

Course outline

Definition of rates and relation between risks and rates; manipulating person-time data in Stata using the st commands; analysis of rates using Mantel-Haenszel methods and Poisson regression; splitting follow up time to allow for exposures that change with time; introduction to survival analysis; log rank tests and Cox proportional hazards regression; graphical displays for survival analysis; Cox models with continuously time-varying covariates; parametric regression using the Weibull and other distributions; analysis of competing risks data using cumulative incidence function and an adapted version of the Cox regression model.

Teaching Time

The teaching time is approximately 18 hours.  

Teaching Methods

Lectures followed by computer practicals using Stata. Group work for interpretation of literature.  

Recommended Reading

For those planning to attend other Departmental statistics courses we would recommend a copy of: Kirkwood BR, Sterne JAC, Essential Medical Statitsics, 2nd ed. Oxford: Blackwell Science 2003 - but it is not compulsory for this course.  

An Introduction to Survival Analysis Using Stata, 3^rd edition. Mario Cleeves, William Gould, Roberto Gutierrez, Yulia Marchenko. Stata Press 2010

Survival Analysis and Epidemiological Tables Reference Manual. Stata Press 2011.

Collett D. Modelling Survival Data in Medical Research. 2nd Edition. Chapman and Hall 2003. Clayton D. and Hills M. Statistical Models in Epidemiology. Oxford University Press 1993.  

Please bring a scientific calculator with you.   

For further information please contact short-course@bristol.ac.uk