Sample size calculations in clinical research should also be based on ethical principles
Bruno Mario Cesana, Paolo Antonelli, Bruno Mario Cesana, Paolo Antonelli
Abstract
Sample size calculations based on too narrow a width, or with lower and upper confidence limits bounded by fixed cut-off points, not only increase power-based sample sizes to ethically unacceptable levels (thus making research practically unfeasible) but also greatly increase the costs and burdens of clinical trials. We propose an alternative method of combining the power of a statistical test and the probability of obtaining adequate precision (the power of the confidence interval) with an acceptable increase in power-based sample sizes.
Keywords: Confidence limits power; Delimited confidence intervals; Ethical principles; Sample size calculation; Statistical power.
References
- Jia B, Lynn HS. A sample size planning approach that considers both statistical significance and clinical significance. Trials. 2015;16:213. doi: 10.1186/s13063-015-0727-9.
- World Medical Association World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. JAMA. 2013;310:2191–4. doi: 10.1001/jama.2013.281053.
- Cesana BM, Antonelli P. A new approach to sample size calculations for the power of testing and estimating population means of Gaussian distributed variables. Biomed Stat Clin Epidemiol. 2010;4:67–78.
- International Conference on Harmonisation. Guidance E9: Statistical Principles for Clinical Trials. September 1998 CPMP/ICH/363/96 (Step 5). . Accessed March 17, 2016.
Source: PubMed