Introduction to Bayesian Methods in Clinical Research [ESP68]

Detailed information about this course:

Description

Faculty: Prof. Emmanuel Lesaffre, PhD

This course provides an introduction to Bayesian methods with an emphasis on the intuitive ideas and applications. The course treats the basic concepts of the Bayesian approach, such as the prior and posterior distribution and their summary measures (mean, median, credible interval, etc), the posterior predictive distribution. In addition, Bayesian methods for model selection and model evaluation will be treated.

The Bayesian approach will also be compared, both conceptually as well as practically, with the classical frequentist approach. Markov Chain Monte Carlo techniques are introduced and exemplified in a variety of applications. The Bayesian approach will be illustrated in clinical trials, epidemiological studies, meta-analyses, diagnostic testing, agreement studies, etc. WinBUGS and OpenBUGS will be used as software. But also the use of their interfaces with R, i.e. R2WinBUGS and R2OpenBUGS will be illustrated.

Course format:

In the first three days of the course the Bayesian concepts will be explained. Theory and exercises will then be mixed depending on the topic. The final two days will be devoted to particular application areas and have largely a practical flavor. In addition the application of the Bayesian methodology in the medical literature will be highlighted.

Teaching methods:

Interactive lectures, exercises, practicals

//Please note that the course information is subject to change and will be updated from time to time. We will do our utmost best to ensure the accuracy and reliability of the information on this website.//

Objectives

• Understanding the Bayesian concepts, able to read medical papers that make use of the Bayesian approach.
• Be able to write a Win/OpenBUGS program for some basic statistical models.
  

Participant profile

Those interested in an alternative approach to analyze data from clinical research, public health research and epidemiology. It is strongly recommended that the participant has a good knowledge in classical statistics, including regression models. Experience with R is also recommended.

Assessment

Attendance