Leaders: Allan Donner, The University of Western Ontario and Neil Klar, Cancer Care Ontario

This course presents a systematic and unified treatment of comparative trials which randomize intact social units, or clusters of individuals, to different intervention groups. Such trials have become particularly widespread in the evaluation of nontherapeutic interventions, including lifestyle modification, educational programmes and innovations in the provision of health care. Their increasing popularity over the last two decades has led to an extensive body of methodology and a growing, but somewhat scattered, literature that cuts across several disciplines in the statistical, social and medical sciences. We will integrate this material into a full day course which emphasizes applications to health research. The overall prerequisite for the course is knowledge of the fundamentals of biostatistics and familiarity with the basic principles of design and analysis of clinical trials. The sequence of topics presented will be based on the recently published text entitled Design and Analysis of Cluster Randomization Trials in Health Research by Allan Donner and Neil Klar (Arnold Publishing Company, London, 2000).

About the Leaders

Dr. Allan Donner is Professor and Chair in the Department of Epidemiology and Biostatistics at the University of Western Ontario in London. He has a special interest in cluster randomization trials and has been involved in several such studies as sponsored by the World Health Organization and the International Vaccine Institute. He is a Fellow of the American Statistical Association and was president of the Biostatistics Section of the Statistical Society of Canada in 1991-1992.

Dr. Neil Klar is a Senior Biostatistician in the Division of Preventive Oncology at Cancer Care Ontario in Toronto. He holds an academic appointment as an Assistant Professor with the Department of Public Health Sciences at the University of Toronto. Neil's research concerns methods for the analysis of correlated outcome data. He is particularly interested in methods for the design and analysis of cluster randomization trials.