Developments in Case-Crossover and Related Designs
• Malcolm Maclure
Adjunct Professor of Epidemiology, Department of Epidemiology; Professor, School of Health Information Science, University of Victoria, Victoria, BC, Canada
• presented by Sander Greenland
Professor, Department of Epidemiology
UCLA Public Health – Epidemiology, Los Angeles, CA, United States

Case-crossover studies test hypotheses about the triggering of events. A case-crossover study can be understood as a highly stratified retrospective analysis of a crossover ‘experiment,’ in which each case serves as his or her own control. In daily life, people cross back and forth between times of exposure and non-exposure, not when an experimenter’s protocol dictates a change in exposure, but when the people decide to change or when their circumstances change. When such crossover data are stratified so each stratum contains only one person, the people without any outcomes (the non-cases) drop out and the analysis is restricted to cases. This presentation includes a pictorial review of the concepts and analytic methods of case-crossover studies, a survey of the domains in which the method has been used, a summary of recent insights from studies of design variants, and its application to investigations of medical errors and adverse effects of drugs using centralized administrative databases. The presentation will be composed by Dr. Maclure and delivered by Dr. Greenland.

Malcolm Maclure, ScD, is a health services epidemiologist specializing in methodology. His forthcoming academic appointment is “British Columbia Chair in Patient Safety” and Professor in the Department of Anesthesiology, Pharmacology and Therapeutics at the University of British Columbia, Vancouver, Canada. He is currently employed as manager of research in the Pharmaceutical Services Division of the British Columbia Ministry of Health in Victoria. From 2002-2006, he was Professor in the School of Health Information Science at the University of Victoria, BC, funded by a Michael Smith Foundation Distinguished Scholar Award. Trained in the Department of Epidemiology at Harvard School of Public Health, he continues his affiliation there as Adjunct Professor. He is current president of the Society for Epidemiologic Research. Among epidemiologists, he is best known for inventing the case-crossover design to study triggers of acute events. He is interested in the causation and measurement of bias in epidemiologic studies. His recent investigations concern drug policy impact evaluations using administrative databases and randomized pragmatic trials. He is exploring the potential to combine these methods to evaluate the effectiveness of drugs in the real world and health system safety improvements.

Sander Greenland is Professor of Epidemiology and Statistics, University of California, Los Angeles.  Professor Greenland has been a leading contributor to epidemiologic statistics, theory, and methods for over three decades.  His major research contributions include assessment of selection bias, misclassification, and confounding effects in epidemiologic research, and critical evaluation of statistical methods for observational studies.  He has authored or co-authored over 300 articles in the health sciences and statistics, as well as the textbook Modern Epidemiology, and has given invited presentations at universities and conferences throughout the world. He has served as an associate editor for several leading journals, and is a Fellow of the American Statistical Association and of the Royal Statistical Society. Professor Greenland received Bachelor's and Master's degrees in mathematics from the University of California Berkeley, and Master's and Doctoral degrees in Epidemiology from the University of California Los Angeles.