Questions We Forget To Ask When Designing an RCT
2026
bayes
design
drug-development
drug-evaluation
endpoints
inference
measurement
multiplicity
p-value
posterior
RCT
sample-size
sequential
Randomized clinical trial designs tend to be traditional, and there is a lot of inertia working against the use of modern designs. There are also a lot of futile RCTs, many resulting from the use of fixed sample sizes powered to detect a level of therapeutic effectiveness that is greater than the minimum clinically important difference. When there are multiple outcome components, it is not uncommon for a trial to result in confusion about which treatment provides the most benefit to patients. This talk asks a series of questions that statisticians and clinical trialists should answer before accepting the status quo.
- Events
- JHU Trial Innovation Center DIDACT Symposium 2026-04-16
- Slides