Skip to main content

Guest Speakers

Richard Cook


Dr. Richard J. Cook is Professor of Statistics in the Department of Statistics and Actuarial Science at the University of Waterloo and Tier I Canada Research Chair in Statistical Methods for Health Research. He was elected Fellow of the American Statistical Association in 2008 and currently holds cross-appointments at the School of Public Health and Health Systems at the University of Waterloo and the Faculty of Health Science at McMaster University. Professor Cook’s research interests include the analysis of life history data, the design and analysis of clinical and epidemiological studies, and statistical methods for incomplete data. Areas of collaboration in health research include cancer, rheumatic disease and transfusion medicine.

Statistical concepts for dependent observation schemes in the analysis of clinic registry data

Disease registries and other sources of administrative data are increasingly available for modeling the course of chronic conditions and other life history processes. Multistate models offer a powerful basis for such analyses but when clinic visit times or loss to followup times are associated with the life history process of interest, biased estimates are obtained from standard analyses. Joint models are presented for the life history, clinic visit, and loss to followup processes to provide a basis for discussing independence conditions for observation processes and a valid approach to analysis. Markov and semi-Markov intensity-based models are considered for the visit process and we discuss likelihood construction when distinguishing between disease-driven and conditionally independent visit times. The impact of misspecifying the visit process intensities is explored and the importance of collecting data on the nature of clinic visits in joint models is highlighted.

Sue Todd


Dr. Sue Todd is Professor of Medical Statistics within the Department of Mathematics and Statistics at the University of Reading, UK and has 25 years of experience as an applied academic statistician working in the fields of clinical trials and epidemiology. Professor Todd’s particular research areas of interest are adaptive designs and sequential clinical trials. Recent research has considered methodology for novel study design and analysis, in particular seamless phase II/III clinical trials involving treatment / subgroup selection and multiple endpoints of interest.


Key Analysis Considerations in Efficient Study Designs

‘Efficient study designs’ is an umbrella term for smarter ways of doing trials. Examples include adaptive designs, cluster randomized trials, SMART studies and randomized registry trials. This presentation will review the important considerations for researchers when implementing and analyzing such studies and will build on the earlier session which explored design features. The focus will be on practical issues and statistical aspects.

Back to top

© Concordia University