Improving Precision and Power in Randomized Trials By Leveraging Baseline Variables
- Summer Inst. term
- 0.5 credits
- Academic Year:
- 2022 - 2023
- Instruction Method:
- Synchronous Online
- Wed 06/29/2022 - Wed 06/29/2022
- Class Times:
- Wednesday, 9:00am - 1:20pm
- Auditors Allowed:
- Undergrads Allowed:
- Grading Restriction:
- Letter Grade or Pass/Fail
- Course Instructor:
- Michael Rosenblum
- Frequency Schedule:
- One Year Only
The prerequisite knowledge is that participants should be familiar with the following concepts: type I error, power, bias, variance, and confidence intervals.
Do you want to learn about recent advances in how to draw precise, reliable inferences from clinical trial data?
Are you curious how it can be applied to improve precision and speed up trials such as trials for COVID-19 treatments and vaccines (and many other disease areas)?
Covariate adjustment is a statistical method for improving precision and power in clinical trials by adjusting for pre-specified, prognostic baseline variables. The resulting sample size reductions can lead to substantial cost savings.
Explains what covariate adjustment is, how it works, when it may be useful to apply, and how to implement it (in a preplanned way that is robust to model misspecification) for a variety of scenarios. Demonstrates the impact of covariate adjustment using trial data sets in multiple disease areas. Provides step-by-step, clear documentation of how to apply the software in each setting. Applies the software tools on the different datasets in small groups.
- Learning Objectives:
Upon successfully completing this course, students will be able to:
- Identify the key concepts from the recent (May 2021) draft guidance from the FDA on covariate adjustment in randomized trials
- Articulate the benefits and limitations of using covariate adjustment to analyze data from randomized trials
- Apply covariate adjustment to improve precision and speed up trials
- Implement covariate adjustment on simulated data sets
- Perform a covariate adjusted data analysis
- Methods of Assessment:
This course is evaluated as follows:
- 40% Participation
- 40% Discussion
- 20% Discussion Board
- Instructor Consent:
No consent required