Bayesian Hierarchical Models
Course Organisers: Sylvia Richardson and John Molitor
19th-21st September 2007
Imperial College London, Faculty of Medicine, St Mary's Campus, Norfolk Place, London W2 1PG
Course outline
Bayesian hierarchical modelling (BHM) is one of the most powerful modern statistical techniques. It provides a unifying framework for dealing with a diversity of sources of complexity arising from the structure (e.g. dependence) of the data and its associated measurement process. Bayesian hierarchical models, coupled with efficient computational tools (MCMC), have been successfully used in a wide range of applications (e.g. epidemiology, social sciences, environmental sciences, genetics).
This course is intended to provide an introduction to the principles and use of Bayesian hierarchical models and associated computations. There is a large practical component to this course with time for hands-on data analysis using the WinBUGS software. The practical exercises will be centred on real case studies. Topics covered will include:
Introduction to complex Bayesian modelling, Bayesian graphical and hierarchical models, Bayesian computation and Markov chain Monte Carlo methods (Gibbs and Metropolis and other samplers), Introduction to model criticism and comparison of BHMs, Prior distributions and sensitivity analysis for hierarchical models, More complex hierarchical models, including models for longitudinal data, temporal and spatial models, Measurement error and missing data, Practical experience of model formulation and of using the WinBUGS software.
Course fees
£680 Industry (Including Catering, Course Documentation and Course Dinner)
£450 Academic, inc. non-profit organisations (Including Catering, Course Documentation and Course Dinner)
£300 Students and Imperial Staff (Including Catering, Course Documentation
and Course Dinner)
Who should attend -
This intermediate level course is designed to be of interest to researchers in statistics and biostatistics or those interested in quantitative applications in epidemiology, medicine, biological sciences, social sciences and environmental science, plus individuals with a general interest in understanding and applying advanced quantitative Bayesian methods.
This course assumes a good grasp of basic statistics, including linear and generalised linear regression analysis. It is recommended that students should have some previous experience of Bayesian concepts and a minimum contact with the WinBUGS software, although this is not essential.
Registration
http://www5.imperial.ac.uk/medicine/coursebookings/bayesian_0709.html
Please remember that your booking is not guaranteed until we receive payment and funds have cleared.
For any other information please contact:
Madeline Kirk - 020 7594 3319 - [log in to unmask]
|