User:Dmfinkelstein/sandbox

David Alan Schoenfeld
David Alan Schoenfeld is a biostatistician best known for methods that advanced the analysis of failure time data from clinical trials and observational studies. He is Professor of Medicine at Harvard Medical School and a Professor in the Department of Biostatistics at the Harvard T.H. Chan School of Public Health. He is the founder and first director of the Biostatistics Center at the Massachusetts General Hospital.

Career

Dr. Schoenfeld obtained his PhD in Mathematics with a statistics concentration at the University of Oregon in 1974. He has been at Massachusetts General Hospital since 1984 and a Professor at Harvard University since 1998. He has been the Group Statistician and Director of the Clinical Coordinating Center for trials in Acute Respiratory Distress Syndrome since 1994. He was the founder and first director of the Biostatistics Center at Massachusetts General Hospital from 1985-2008. Throughout his career, he has been a lead statistician in clinical cooperative groups, including the Eastern Cooperative Oncology Group, the Radiation Therapy Oncology Group, the AIDS Clinical Trials Group and the Northeast ALS Consortium.

Research and Contributions

Dr. Schoenfeld started his career as a biostatistician at the Dana-Farber Cancer Institute in 1975. The Proportional hazards model had recently been proposed as the primary method of analyzing clinical trials in oncology that used patient survival to measure treatment efficacy. Methods for survival analysis had to tackle the issue of censoring which occurs because the failure time may not be observed for all subjects. He developed a graphical method for assessing goodness of fit to the proportional hazards model, described in a publication that has had over 1700 citations in the medical and statistical literature, that is available in most major software packages as the "Schoenfeld Residuals". The residuals are the individual contributions to the score statistic for the model at each event time and would be independent of time if the proportional hazards model holds. Dr. Schoenfeld also contributed to the methods for designing studies for which failure time was the primary outcome. He showed how to calculate the power, efficiency and sample size for a wide class of tests comparing survival distributions, including the logrank test. He recognized that the power of a study using covariates is determined by the number of failures and the hazard ratio between the treatment groups, and provided simple programs for designing the trial. He developed one of the first web sites for designing clinical trials. He has written papers on methods for study design for clinical trials of AIDS, Acute Respiratory Distress Syndrome, Amyotrophic Lateral Sclerosis and Major Depressive Disorder. He has over 370 articles in peer-reviewed academic journals.

Awards and Recognition

In 1991 he was elected as a member of the International Statistical Institute, in 1992 he was elected as a Fellow of the American Statistical Association, in 2017 he was named “Statistician of the Year” by the Boston Chapter of the American Statistical Association , and in 2018 he was elected a Fellow of the Institute of Mathematical Statistics.