Short Courses
 


Short courses will be held on the days prior to the conference opening. Details are below and places can be reserved by completing the short course registration form.

Course fees are $450 per person, with a reduced fee of $250 per person for students and attendees from special circumstance countries. A discounted fee will be applicable for those participants attending two courses. Course materials, lunch, tea and coffee are included in the fee.

Please note that minimum numbers apply for these courses and the organisers reserve the right to cancel should these numbers not be met. The option of choosing another course or a full refund of the short course fee will be given to delegates if a course is cancelled for this reason.

Please click the button below to open the registration form for IBC Short Courses.

top

Longitudinal and Incomplete Data Analysis
Saturday 10 July 2004
8.30am – 5.30pm
Radisson Plaza Hotel, Cairns

Presenters
Professor Geert Molenberghs, Limburgs Universitair Centrum, Belgium and
Professor Geert Verbeke, Royal University of Leuven, Belgium

Biographies
Geert Verbeke is Associate Professor of Biostatistics at the Biostatistical Centre of the Katholieke Universiteit Leuven in Belgium. He wrote his dissertation as well as a number of methodological papers, on various aspects of linear mixed models for longitudinal data.

Geert Molenberghs is Professor of Biostatistics at the Limburgs Universitair Centrum in Belgium. He published methodological work on repeated categorical data and on the analysis of nonresponse in clinical and epidemiological studies.

Both presenters are editor and author of two books on the use of linear mixed models for the analysis of longitudinal data (Springer Lecture Notes 1997, Springer Series in Statistics 2000), and they have taught several (short) courses on the topic in universities as well as industry.

Course Description
The course consists of three main parts: continuous longitudinal data, discrete longitudinal data, and incomplete data.

Based on Verbeke and Molenberghs (Springer, 1997, 2000), and the forthcoming Molenberghs and Verbeke (2004), a general introduction to longitudinal data and the linear mixed model for continuous responses will be presented. The topic will be approached from the modeller's and practitioner's points of view. Emphasis will be on model formulation, parameter estimation, and hypothesis testing, as well as on the distinction between the random-effects (hierarchical) model and the implied marginal model. Apart from classical model building strategies, many of which have been implemented in standard statistical software, a number of flexible extensions and additional tools for model diagnosis will be indicated. Illustrations will be given based on the SAS procedure MIXED.

When the response of interest is categorical, a number of modeling options are open. One can choose between marginal, conditional, or random-effects models. For example, the linear mixed model concepts can be extended towards generalized linear mixed models. Within the marginal family, an important alternative approach is the use of generalized estimating equations (GEE). A lot of emphasis will be put on the fact that the regression parameters obtained from models within different families, have different interpretations. Advantages and disadvantages of various procedures will be discussed and compared in detail, and illustrations will be based on the SAS procedures GENMOD and NLMIXED. Some other approaches will be sketched briefly.

Finally, when analysing longitudinal data, one is often confronted with missing observations, i.e., scheduled measurements have not been made, due to a variety of (known or unknown) reasons. It will be shown that, if no appropriate measures are taken, missing data can cause seriously biased results, and interpretational difficulties. A general framework to deal with incomplete longitudinal data will be formulated, and the advantages and disadvantages of various approaches will be highlighted.

Although the course will be to a large extent software-free, SAS users could benefit from downloading some of the datasets from the instructors' web sites, in order to enhance their practical skills.

top

Using the R System for Data Analysis and Graphics
Sunday 11 July 2004
8.30am – 5.30pm
Radisson Plaza Hotel, Cairns

Presenter
Dr Bill Venables, CSIRO, Australia

Biography
After graduating from the University of Queensland in 1966, Dr Bill Venables began work, initially as a statistical consultant and then as a lecturer at the University of Adelaide. In 1999 he changed careers and joined CSIRO,
where he is a group leader in the Environmental Measurement and Assessment programme of the Division of Mathematics and Information Sciences (CMIS).

He collaborates closely with marine scientists in a sister division, Marine Research (CMR) and works mostly on marine problems of fishery and ecosystem sustainability. Bill is a long-time contributor first to the S, then the
S-PLUS and now the R and S-PLUS community. He has written over 80 research articles and co-authored two books with Brian Ripley on using S for data analysis and graphics, both of which enjoy classic status with some groups of readers. He is a frequent contributor to R-help and S-news and for over twelve years has regularly given workshops and short courses on programming, data analysis and graphics using the S language, mainly in Australia, but also in New Zealand, Germany, Holland, the UK and the USA.

Course description
This one-day course will cover aspects of using R at two levels.

    In the morning course we deal with:
  • setting up the system (about 15 mins)
  • getting started
  • data input and output
  • graphics
  • basic data structures
  • installing and using libraries
  • elementary linear and generalized linear modelling.

    In the afternoon session we give some key details on:
  • more advanced aspects of graphics and modelling
  • programming effectiveness and efficiency
  • setting up libraries of your own functions, data sets
  • using compiled code within R as dynamic link libraries (dll's).

Participants will be expected to bring their own laptops and to have downloaded the specified software and datasets prior to arriving in Cairns, or to purchase CDs with the same on site. Those paying the reduced fees will be able to share a laptop if necessary. If possible we plan to hold free and informal tutorial sessions at convenient times while the conference is in progress to reinforce the material and answer subsequent questions.

top

Statistics for Microarray Data Analysis
Sunday 11 July 2004
8.30am – 5.30pm
Radisson Plaza Hotel, Cairns

Presenters
Professor Terry Speed, University of California at Berkeley, USA and
Dr Gordon Smyth, Walter and Eliza Hall Institute of Medical Research, Australia

Biographies
Terry Speed's current research concerns the application of statistics to problems in genetics and molecular biology. These have provided many novel challenges of both an applied and a theoretical nature. His major interests within this area are in the mapping of genes in mice and humans, including disease genes and genes contributing to the variation of quantitative traits, and the statistics of production DNA sequencing. The Human Genome Project has been a stimulus for a number of the problems he has investigated with his students. Other areas of interest include the analysis of DNA and protein sequences, for example, the statistics of database searches and of finding genes in DNA sequence, and the analysis of microarray data. He is currently on the
editorial board of the Journal of Computational Biology. With Deborah Nolan, he has written a textbook which teaches through case studies "STAT LABS: Mathematical Statistics Through Applications"

Gordon Smyth is Senior Research Scientist in Bioinformatics at the Walter and Eliza Hall Institute of Medical Research. He works on a range of bioinformatics problems and especially on the design and analysis of gene expression microarray experiments. Before moving to the WEHI, he was Director of the Centre for Statistics at the University of Queensland. He is a core member of the Bioconductor project and the primary author of the popular package LIMMA for R for analysis of designed microarray experiments. He actively collaborates with biologists around Australia and internationally on microarray analysis projects. He is regularly invited to speak on microarray analysis topics.

Course Description
Microarray technology, which provides a way to globally measure differential gene expression, promises to be extremely useful for the diagnosis, treatment, and prevention of complex disease as well as for the elucidation of biological mechanisms. These studies yield tens of thousands of simultaneous gene measurements from each biological sample. Issues in measurement and calibration of the microarrays need to be addressed appropriately in order to obtain valid datasets. To gain insight into genes and their function, patterns of expression and expression changes must then be discerned from high-dimensional data in which the number of observations is small relative to the number of variables. The purpose of the one-day short course in Statistics for Microarray Data Analysis is to introduce statisticians and other researchers to statistical issues in the design and analysis of microarray studies of current interest to biologists and biomedical researchers.

Experience with statistical methods and in data analysis is a pre-requisite, but no previous exposure to microarray data is assumed. The course will include the opportunity for participants to apply statistical methods to several datasets that will be provided.

Participants will be expected to bring their own laptops and to have downloaded the specified software and datasets prior to arriving in Cairns, or to purchase CDs with the same on site. Those paying the reduced fees will be able to share a laptop if necessary.

top