Short Course on Graphical Models for Observational Data

Wednesday - Friday, 22-24 June 2011

University of Queensland

The School of Population Health, University of Queensland and the Statistical Society of Australia, Inc. are hosting a two day introductory course and an advanced day on Graphical Modelling of Observational Data in Brisbane, to be presented by Professor Joe Whittaker, Lancaster University.

 

Guest Lecturer: Professor Joe Whittaker

Department of Mathematics and Statistics,

Lancaster University, UK

 

  

I. Introduction to Graphical Modelling of Observational Data using R (2 days)

9:00am–5:00pm, Wednesday & Thursday 22-23 June 2011

 

II. Advanced Topics in Graphical Modelling of Observational Data (3rd day)

9:00am–5:00pm, Friday 24 June 2011

 

Location: Room 434, Public Health Building, University of Queensland, Herston Campus.

  

A particular problem of statistical data analysis is to model the inter-dependencies among a set of response variables. Graphical models, based on conditional independence, provide a powerful and informative toolbox for unravelling manifest interactions and associations. 

This course discusses undirected graphical models, describing their properties and their statistical analysis. The course is not mathematical but sometimes phrased in mathematical notation, for example X $\perp$ Y denotes that X and Y are independent. It updates the material in Whittaker, J (1990) Graphical models in applied multivariate statistics, Wiley. Many examples of successful analyses drawn from the social, biological and  physical sciences are given. 

Novel features of this course are the emphasis on weighted independence graphs, a review of modern search methods and a survey of R packages useful to graphical modelling. Using R from inside Microsoft Excel and statistical packages such as stata, SAS and SPSS will also be briefly outlined. 

This will be a lecture course with software demonstrations and some hands-on practicals. Sessions will be roughly 90 minutes long and most sessions will include short practicals. 

Participants will be expected to have R and appropriate graphical modelling packages installed on their own laptop. Details and help with installations will be provided to participants prior to the course. 

Participants are encouraged to bring a data set of their own to explore during the course.

 

                                                                                                                         

  

Introductory Seminar

Professor Whittaker will also present an initial seminar on Tuesday 21 June highlighting interesting results from novel application of graphical modelling. The talk will give the barest outline of the theory, together with examples from protein analysis, adverse events in clinical trials, and smoking and dropout in longitudinal studies.

 

Presenter 

Professor Joe Whittaker is a long term member of the Department of Mathematics and Statistics, Lancaster University. He is a fellow of the Royal Statistical Society, a past member of its Council, of its Research Section, and past chairperson of its Multivariate Study Group. He has been a member to the Board of Directors of the European Region of the International Association for Statistical Computing. He has held visiting Professorships in the Department of Statistics at Colorado State University and at the University of Chicago. His main research interests lie in graphical modelling. Previous courses have been sponsored by the ESRC, and have been given in England, Belgium, Holland, France, Italy, Spain, Switzerland, Brazil and the USA. He is the author of Graphical Models in Applied Multivariate Statistics, published by Wiley.

 

Registration and Course Fees:

 

Registration before                     Friday 6 May 2011                    Registration after Friday 6 May 2011

                                                      2 days ($)   3 days ($)                      2 days ($)        3 days ($)

SSAI and Academic                   450              650                                  650                     900

Full                                                600              800                                  800                    1050

Student                                         300              400                                  400                     525

 

Please note that an early bird discount will apply to registrations paid by Friday 6 May 2011. There is allocation for a limited number of places on the course for University of Queensland staff and enrolled students at a discounted rate. If you wish to enquire about these positions or for further information please contact Dr Peter Baker.

                                                                                                                       

Enquiries

Dr Peter Baker

School of Population Health, University of Queensland, Herston, QLD

Email: p.baker1@uq.edu.au         WWW: http://www.sph.uq.edu.au/

Phone: +61 7 3346 4747              Fax: +61 7 3365 5442

To download a workshop flyer with the registration form, please click here.