Related Experiment Videos
Adaptive statistical analysis following sample size modification based on interim review of effect size
H M James Hung1, Lu Cui, Sue-Jane Wang
1Division of Biometrics I, OB/OPaSS/CDER, FDA, Rockville, Maryland, USA. hung@cder.fda.gov
Journal of Biopharmaceutical Statistics
|July 19, 2005
Summary
Clinical trial success hinges on accurate sample size, which depends on unknown effect size. This study explores sample size re-estimation using interim analysis for adaptive trial designs, improving upon fixed designs.
Area of Science:
- Clinical Trials
- Biostatistics
- Medical Research Methodology
Background:
- Sample size calculation is critical for clinical trial success.
- Accurate estimation of effect size is challenging, often relying on historical data.
- Overestimating effect size can lead to insufficient sample size, jeopardizing trial outcomes.
Purpose of the Study:
- To motivate the use of sample size re-estimation in clinical trial planning.
- To introduce a simple adaptive test strategy based on interim effect size analysis.
- To evaluate the performance of adaptive designs against fixed sample size designs.
Main Methods:
- Developing a sample size re-estimation procedure.
- Implementing an adaptive test strategy utilizing interim analysis results.
- Comparing the adaptive design with a fixed maximum sample size design.
Main Results:
- Sample size re-estimation based on interim effect size provides a robust adaptive strategy.
- Adaptive designs offer improved performance compared to traditional fixed sample size designs.
- The proposed method addresses the risks associated with inaccurate initial sample size estimations.
Conclusions:
- Sample size re-estimation should be a key consideration in clinical trial design.
- Adaptive trial designs incorporating interim analyses enhance statistical power and efficiency.
- This approach mitigates the risk of underpowered trials due to effect size misestimation.