The proposed five-year program is designed to train biostatisticians to conduct biostatistical research relevant to important problems in the areas of cardiovascular disease clinical trials and to provide high-level collaborative research and consulting support to other research workers in the cardiovascular disease clinical trials field. The training is directed at the predoctoral level. The academic courses will include all those in theoretical and applied statistics, which are the core of a doctoral degree program for a statistician working in the health sciences, plus relevant courses in clinical trials methodology and cardiovascular diseases. Biostatistical training in research and consultation will focus on such important areas as the design of clinical trials, longitudinal trials, and cross-over designs, sequential analysis, data management, survival analysis, quality control and measurement issues, resampling methods in clinical trials, empirical Bayes and Bayes methodologies. The typical predoctoral trainee will be a college graduate with an excellent undergraduate record, expertise in mathematics to the level of multivariable calculus. Stipends and associated support are requested for five predoctoral trainees for five years. The Department of Biostatistics as a component of the School of Public Health, has available to it all the personnel and facilities sufficient to provide a very comprehensive training program in cardiovascular disease clinical trials.
Muller, Keith E; Edwards, Lloyd J; Simpson, Sean L et al. (2007) Statistical tests with accurate size and power for balanced linear mixed models. Stat Med 26:3639-60 |
Sterrett, Andrew; Wright, Fred A (2007) Inferring the location of tumor suppressor genes by modeling frequency of allelic loss. Biometrics 63:33-40 |
Edwards, Lloyd J; Stewart, Paul W; MacDougall, James E et al. (2006) A method for fitting regression splines with varying polynomial order in the linear mixed model. Stat Med 25:513-27 |
Greene, Wendy F; Cai, Jianwen (2004) Measurement error in covariates in the marginal hazards model for multivariate failure time data. Biometrics 60:987-96 |