Education > Continuing Education > LearnSTAT Courses
|
Course Descriptions and Information |
Survival Analysis in Clinical Trials |
|
|
Presented by Danyu Lin, Department of Biostatistics, University of North Carolina at Chapel Hill One-day Course Thursday, April 30: 9:00 a.m. - 5:00 p.m. |
|
Course Description |
|
| The primary outcome measure in a clinical trial designed to provide a reliable assessment of benefit and risk is often defined to be the time to occurrence of a clinically important event, such as death, cancer recurrence and stroke. A common complication is that a substantial fraction of the trial participants remain free of the study endpoint at the end of follow-up so that their event times are censored. Special statistical methods have been developed to provide valid and efficient evaluations of treatment effects on potentially censored event times. This course will offer an overview of such methods, focusing on the commonly used Kaplan-Meier estimator, log-rank test and Cox proportional hazards model. We will address practical issues in clinical trial applications, including sample size determination, sequential analysis, covariate adjustment, and model diagnostics. Recent developments in the areas of multiple events, informative drop-out, and joint modeling of repeated measures and event times will also be discussed. Relevant software will be described. Detailed illustrations with real data will be provided throughout the course. The materials will be presented at a non-technical level. Although cutting-edge research will be discussed, this course is targeted primarily at clinical trial statisticians who wish to analyze their data with the best available methods. Basic knowledge of mathematical statistics and linear models is required. Background on survival analysis is not necessary. There is no required textbook. A useful reference is: Fleming, T. R. and Lin, D. Y. (2000). Survival analysis in clinical trials: past developments and future directions. Biometrics, 56, 971-983 (Editors' Invited Paper). |
|
Presenter |
|
| Danyu Lin is the Dennis Gillings Distinguished Professor of Biostatistics at the University of North Carolina at Chapel Hill. Professor Lin is an internationally recognized expert in survival analysis. He has published over 120 peer-reviewed papers, most of which appeared in premier statistical journals. Several of his methods have been incorporated into commercial software packages, such as SAS, S-Plus and STATA, and widely used in practice. Professor Lin is on Thomson ISI's list of Highly Cited Researchers in Mathematics. He is a former recipient of the Mortimer Spiegelman Gold Medal from the American Public Health Association and a Fellow of both the American Statistical Association and the Institute of Mathematical Statistics. He currently serves as an Associate Editor of Biometrika and a Consultant to the FDA. | |
Return to Survival Analysis in Clinical Trials & Introduction to Meta-Analysis |
|
Introduction to Meta-Analysis |
|
|
Presented by Michael Borenstein, Biostat One-day Course Friday, May 1: 9:00 a.m. - 5:00 p.m. |
|
Course Description |
|
|
Meta-Analysis is a set of statistical procedures used to synthesize results from a series of studies. When the treatment effect is consistent from study to study, meta-analysis allows us to compute a combined effect with greater precision than any of the single studies. When the effect varies from study to study, meta-analysis allows us to assess, and possibly to explain the variation as a function of study-level moderators. Researchers and organizations publish meta-analyses that establish the impact of treatments and serve to inform policy. Pharmaceutical companies use meta-analyses to synthesize the results of studies for submissions to the FDA, and to make a compelling case for the impact of drugs as part of post-approval marketing programs. This course will offer an overview of all phases of a meta-analysis, including the goals, the computational issues, and the interpretation. We will discuss various computational models (fixed effect, random effects, mixed models), explain the conceptual differences among these models, and then show how this translates into different computational formulas. We will also work through examples using several computer programs. Finally, we will discuss some of the controversy surrounding meta-analysis, with many journals treating meta-analysis as the highest standard of evidence with others seeing it as problematic. |
|
Presenter |
|
| The course will be taught by Dr. Michael Borenstein. Dr. Borenstein served for 22 years as Director of Biostatistics at the Long Island Jewish Medical Center, and as Associate Professor at Albert Einstein College of Medicine. He is co-author of "Introduction to Meta-Analysis", and "Effect sizes for Meta-Analysis" both to be published by Wiley later this year, and co-editor of "Publication Bias in Meta-Analysis", published by Wiley in 2005. He is also the PI on a series of NIH grants to develop software for meta-analysis, and lead developer of the program Comprehensive Meta-Analysis. Dr. Borenstein has taught short courses on meta-analysis in many venues in the US, Europe, and Australia over the past ten years. | |
Return to Survival Analysis in Clinical Trials & Introduction to Meta-Analysis