Bruce Levin, Ph.D., is Professor Emeritus of Biostatistics at the Mailman School of Public Health. He taught at Columbia for 45 years from 1974 until his retirement in 2019. He was Chair of the Department of Biostatistics from 2000 to 2011, during which time the department enjoyed dramatic growth, tripling the number of faculty, and was ranked third in the nation in a 2007 study conducted by the Chronicles of Higher Education.
Dr. Levin has a long-standing interest in statistical methodology for clinical trials, public health, and the law. Using sequential statistical methods, he has published on innovative trial designs, e.g., designs that minimize ethical costs, designs that emphasize the selection paradigm rather than the significance testing paradigm, and novel designs such as the comparative selection trial which combines features of both paradigms. An example is the QALS trial (high-dose coenzyme Q10 in ALS disease), a phase II design that combined a selection phase with a non-superiority (futility) phase utilizing the same data. In May of 2009 he gave a short course to the FDA/CDER biostatistics group entitled, “Selection Methods in Clinical Trials.” He continues to publish mathematical articles in the area of sequential selection procedures.
Dr. Levin enjoys putting theory into practice and has served as the senior statistical consultant on several multicenter randomized clinical trials in the field of stroke neurology and cardiology, including the WARCEF trial (Warfarin versus Aspirin in Reduced Cardiac Ejection Fraction), the WARSS trial (Warfarin versus Aspirin in Recurrent Stroke Study), the GAIN Americas trial, and the CABG Patch trial. In addition to these aging-related diseases, Dr. Levin has collaborated for many years with epidemiologists studying reproductive aging. He also served for over 20 years as the Director of the Statistics, Epidemiology, and Data Management (SED) Core of the HIV Center for Clinical and Behavioral Studies. He continues to be actively engaged in several Data Monitoring Committees for randomized controlled trials.
Dr. Levin is an elected Fellow of the American Statistical Association. He served for ten years as Consulting Statistical Editor for the American Journal of Public Health and is a Statistics Section Award winner of the American Public Health Association. He is co-author of the 3rd edition of Statistical Methods for Rates and Proportions with Myunghee Cho Paik and the late Joseph L. Fleiss (Wiley, 2003). Dr. Levin is also co-author with Michael O. Finkelstein of Statistics for Lawyers, 3rd Ed. (Springer, 2015), and has testified in many court cases as a statistical expert. Dr. Levin’s most recent book is The Biostatistics of Aging (Wiley, 2014), co-authored with Dr. Gilberto Levy.
Education and Academic Positions
Columbia University 1968 B.A. (Mathematics)
Harvard University 1972 M.A. (Mathematics)
Harvard University 1974 Ph.D. (Applied Mathematics and Statistics)
The website http://www.columbia.edu/~bl6/publist.htm contains a complete listing of Dr. Levin’s publications.
- Lai, T.L., Levin, B., Robbins, H. and Siegmund, D. (1980). Sequential Medical Trials. Proceedings of the National Academy of Sciences USA 77(6):3135-3138.
- Levin, B. and Robbins, H. (1981). Selecting the Highest Probability in Binomial or Multinomial Trials. Proceedings of the National Academy of Sciences USA 78(8):4663–4666.
- Levin, B. (1981). A Representation for Multinomial Cumulative Distribution Functions. Annals of Statistics 9(5):1123–1126.
- Levin, B. (1987). Conditional Likelihood Analysis in Stratum–Matched Retrospective Studies with Polytomous Disease States. Communications in Statistics B16(3):699–718.
- Levin, B. (1990). The Saddlepoint Correction in Conditional Logistic Likelihood Analysis. Biometrika 77(2):275–285.
- Levin, B. and Kong, F. (1990). Bartlett's Bias Correction to the Profile Score Function is a Saddlepoint Correction. Biometrika 77(1):219–221.
- Leu, C.-S. and Levin, B. (2008). On a Conjecture of Bechhofer, Kiefer, and Sobel for the Levin-Robbins-Leu Binomial Subset Selection Procedures. Sequential Analysis 27:106-125.
- Levin, B., Thompson, J.L.P., Chakraborty, B., Levy, G., MacArthur, R.B., Haley, E.C. (2011). Statistical Aspects of the TNK-S2B Trial of Tenecteplase versus Alteplase in Acute Ischemic Stroke: An Efficient, Dose-Adaptive, Seamless Phase II/III Design. Clinical Trials 8:398-407.
- Leu, C.-S., Cheung, Y.-K., and Levin, B. (2011). Subset selection in comparative selection trials. In: Bhattacharjee, M., Dhar, S.K., and Subramanian, S. (eds.) Recent Advances in Biostatistics: False Discovery, Survival Analysis, and Other Topics. Series in Biostatistics, 4:271-288. World Scientific.
- Levin, B. and Leu, C.-S. (2013). On an Inequality That Implies the Lower Bound Formula for the Probability of Correct Selection in the Levin-Robbins-Leu Family of Sequential Binomial Subset Selection Procedures. Sequential Analysis 32(4):404-427.
- Caplan, A., Plunkett, C., and Levin, B. (2015). Selecting the Right Tool for the Job (invited paper). American Journal of Bioethics 15(4):4-10, with open peer commentaries pp. 33-50, and response pp. W8-W10.
- Levin, B. (2015). The Futility Study—Progress Over the Last Decade. Contemporary Clinical Trials 45(Pt A):69-75.
- Levin, B. and Leu, C.-S. (2016). On Lattice Event Probabilities for Levin-Robbins-Leu Subset Selection Procedures. Sequential Analysis 35(3):370-386.
- Levin, B. and Leu, C.-S. (2020). Positivity of Cumulative Sums for Multi-Index Function Components Explains the Lower Bound Formula in the Levin-Robbins-Leu Family of Sequential Subset Selection Procedures. Sequential Analysis 39(4) (in press).
Last updated October 9, 2020