Related Experiment Videos
Optimal sample size for a series of pilot trials of new agents
T J Yao1, C B Begg, P O Livingston
1Department of Epidemiology and Biostatistics, Memorial Sloan-Kettering Cancer Center, New York, New York 10021, USA.
Abstract:
A new approach is presented for determining the appropriate sample sizes for a series of screening trials to identify promising new therapeutic agents. The formulation of the problem is motivated by recognition of the fact that screening of new agents is a continuing process. Consequently, it does not seem ideal to fix the overall total sample size, as previous authors have done. Instead we fix the error rates and optimize the individual sample sizes to minimize the time to identify a promising agent, using an empirical Bayes formulation. When applied to data from the large historical experience of exploratory vaccination trials at Memorial Sloan-Kettering Cancer Center, the method demonstrates that relatively small individual screening trials are optimal in this setting. The reliability of the results is evaluated using bootstrapping techniques.
Insights
This study introduces a new method for optimizing sample sizes in therapeutic agent screening trials. It suggests smaller, continuous trials are more efficient for identifying promising agents over time.
Area of Science:
- Biostatistics
- Clinical Trial Design
- Pharmacological Screening
Background:
- Therapeutic agent screening is an ongoing process, necessitating adaptive strategies.
- Traditional fixed total sample size approaches may not be optimal for continuous screening.
- Minimizing the time to identify promising agents is a key objective in drug discovery.
Purpose of the Study:
- To develop a novel approach for determining optimal sample sizes in sequential screening trials.
- To address the limitations of fixed sample size designs in the context of continuous agent screening.
- To minimize the time required for identifying effective therapeutic agents.
Main Methods:
- An empirical Bayes formulation was used to optimize individual sample sizes.
- Error rates were fixed, while sample sizes were optimized to reduce identification time.
- Bootstrapping techniques were employed to assess the reliability of the proposed method.
Main Results:
- The new approach demonstrated that relatively small individual screening trials are optimal.
- Application to historical vaccination trial data validated the method's efficiency.
- The empirical Bayes formulation effectively balances error rates and sample size optimization.
Conclusions:
- The proposed method offers a more efficient strategy for sample size determination in continuous screening.
- Optimizing individual trial sizes in sequential screening can accelerate the identification of therapeutic agents.
- This approach provides a statistically sound framework for adaptive clinical trial design in drug discovery.