After receiving his Ph.D. from Princeton, Dr. Brown joined the research faculty of the Department of Biomathematics at UCLA. From 1968 to 1981 he was a faculty member of the Department of Statistics at Tel-Aviv University where he developed the statistical consulting laboratory. During this period he also visited UCLA for three years where he was responsible for the development of the categorical data analysis programs in BMDP. Since joining the Department of Biostatistics at the University of Michigan, he has collaborated with medical school colleagues in developing methods for the analysis of hormone data. From 1998-2007, he built the infrastructure to be the data coordinating center for multicenter trials and was the Principal Investigator on two NIH-funded multicenter networks, as well as the director of the data coordinating center for several other trials. His research interests are: Clinical Trials, Categorical Data Analysis, Statistical Computing, Robust Methods and Model Fitting.
- Ph.D., Mathematics (Statistics), Princeton University, 1965
- B.A., Mathematics, McGill University, 1962
Research Interests & Projects
- Our current interest is the design, conduct and analysis of clinical trials, both single center and multi-center trials. We have developed infrastructure to conduct multicenter trials using the Biometrics and Outcomes Research Core as the data coordinating center. We are currently the data coordinating center for several NIH funded multi-center trials; including one on pelvic floor disorders and the other on biliary atresia and other cholestatic diseases in the infant. In addition, my students have developed statistical methods and/or models in response to problems in medicine or biology. Examples of such problems are: (1) A statistic to test for differences between groups when the outcome is continuous and there are dropouts from the study; (2) Improved (more robust) methods that will be used for the analysis of assays of hormones; (3) Methods to identify patterns of secretion of hormones into the blood, such as pulses or cycles; (4) Models of secretion of one hormone as a function of the secretion of a second hormone.
- Carlson N, Johnson T, Brown MB (2009). A Bayesian approach to modeling associations between pulsatile hormones Biometrics in press.
- Luke B, Brown MB, Grainger DA, Stern JE, Klein N, A SART Writing Group (2009). The effect of early fetal losses on singleton assisted-conception pregnancy outcomes Fertility and Sterility in press.
- Luke B, Brown MB (2008). Maternal Morbidity and Infant Mortality in Twin versus Triplet and Quadruplet Pregnancies American Journal of Obstetrics and Gynecology 401.e1-401.e10.
- Luke B, Brown MB (2007). Contemporary Risks of Maternal Morbidity and Adverse Outcomes With Increasing Maternal Age and Plurality Fertility and Sterility 283-293..
- McClure LA and Brown MB (2006). A Likelihood Approach to Analyzing Clinical Trial Data When Treatments Favor Different Outcomes. Contemporary Clinical Trials 340-352.
- Isaman, D. J. M. and Brown, M. B. (2006). A discrete-state discrete-time model using indirect observations. Statistics in Medicine 1035-1049.
- Brown, M. B. (2004). Control groups appropriate for surgical interventions: Ethical and practical issues. Gastroenterology S164-S168.
- Lang, L., Lin, X., Brown, M. B., Gupta, S. and Lee, K-H. (2004). A population pharmacokinetic model with time-dependent covariates measured with errors. Biometrics 451-460.
- Wang, Y., Ke, C. and Brown, M. B. (2003). Shape Invariant Modeling of Circadian Rhythms with Random Effects and Smoothing Spline ANOVA Decompositions. Biometrics 804-812.