Clinical trials proceed with four phases to assess the safety and efficacy of an Investigational Product (IP) [1]. The sample size should be considered with extra care for each of these phases. The outcome of the first three phases determines if the IP can proceed with FDA/Health Canada approval for clinical use. Overestimation or under-estimation of sample size effect on the outcome of a trial.

The sample size in a clinical trial should be large enough to provide a scientific answer to the questions addressed [2]. If we underestimate the sample size in a study, then the selected number of participants will be less than required to answer the question. That affects the outcome by the statistically non-significant result, while the conclusion drawn is incorrect. This poses both scientific and ethical issues for the sponsor by producing inconclusive results and exposing human subjects to the possible risks. That can be avoided by conducting power analysis and calculating the sample size for a study before conducting a trial. If we overestimate sample size, then the selected number of participants will be more than required, and a strong statistical significance may result. However, this raises ethical issues as exposes more participants than necessary to any related risk.

The sample size influences the ethical acceptability of a study. It is unethical if the sample size is not large enough to make certain power or too large to expose many subjects to related risks than necessary.

Also, the sample size calculation is an essential key for budgeting management. It is crucial to balance designing a scientific study trial within the budget before recruiting participants. Clinical trials are costly, and robust budgeting for resource management is necessary.

Calculating sample size with scientific justification is critical for any clinical trial [3].

To answer the question of “How many subjects do I need for my study?” The following items must be answered:

What is the study design?
• What kind of primary outcome variable?
• What is the Standard Normal Distribution?
• What is the desired level of significance (α)?
• What is the desired Power and Confidence Interval (CI)?
• What is the test statistic which will be used for analysis?

Ask a professional clinical research scientist at dicentra to assist with sample size determination for your trial study.

References:

[1] U. S. D. of H. and H. Services and F. and D. Administration, “Step 3: Clinical Research | FDA,” Center for Drug Evaluation and Research (CDER). https://www.fda.gov/patients/drug-development-process/step-3-clinical-research (accessed Sep. 29, 2020).
[2] U. S. D. of H. and H. Services and F. and D. Administration, “E9 Statistical Principles for Clinical Trials | FDA,” Center for Drug Evaluation and Research (CDER). https://www.fda.gov/regulatory-information/search-fda-guidance-documents/e9-statistical-principles-clinical-trials (accessed Sep. 29, 2020).
[3] T. V. Sakpal, “Sample size estimation in a clinical trial.,” Perspect. Clin. Res., vol. 1, no. 2, pp. 67–9, Apr. 2010, Accessed: Sep. 29, 2020. [Online]. Available: http://www.ncbi.nlm.nih.gov/pubmed/21829786.