This year, Bruce Turnbull is the recipient of Cornell's Distinguished Alumni award, presented during the Day of Statistics. He'll also be giving the event's opening talk.
After receiving his doctoral degree, Turnbull was a visiting faculty member at Stanford University with joint appointments in the Department of Statistics and the School of Medicine. In 1972 he was appointed lecturer at the Mathematical Institute, University of Oxford. He joined the Cornell faculty in 1976, where he is currently Professor of Statistics in the Departments of Statistical Science and of Operations Research. In 1979 he was awarded the Snedecor Memorial Award by the American Statistical Association in recognition of his research. He has authored over 100 publications and the co-author of a recent book on statistical procedures for monitoring clinical trials. He has been a consultant to many organizations, including the Oak Ridge National Laboratory. Turnbull has served on the Board of Directors of the National Institute of Statistical Sciences, and on the Expert Review Panel for the National Toxicology Program Board of Scientific Counselors. He is on the Data and Safety Monitoring Committees for several major national and international clinical trials in the areas of cancer, heart disease, pulmonary disease and of AIDS sponsored by the National Institutes of Health and by the Veterans Administration.. He has served on the editorial board of a number of statistical journals. He is a Fellow of the American Statistical Association and of the Royal Statistical Society. He is also a member of the Institute for Operations Research and the Management Sciences, the Biometric Society, and the Institute of Mathematical Statistics. Learn more at his personal webpage.
Title: "Sequential Statistics and Clinical Trials: From Biblical Times to Modern Day Adaptive Designs"
Abstract: We start with a (thankfully) brief account of personal reminiscences and lessons learned during the author’s career emphasizing the eclectic nature of our profession. We then mention some historical events in the history of clinical trials and of sequential experimentation, leading up to the introduction of formal group sequential methods starting in the 1980’s. About 20 years later, a variety of methods were introduced under the umbrella name of “flexible” or “adaptive” designs, whereby valid inferences could be made even in the presence of data-driven mid-course changes in the experimental protocol. However such flexibility does not come without cost in terms of power and sample size. We investigate the situation where it is desired to modify sample sizes mid-course when ideas about the effect size to be detected with a given power can change. Finally we describe how an optimal sequential plan can be constructed. This can serve as a benchmark for evaluating various ad hoc plans that have been proposed in the literature.