How to Determine the Sample Size in a Clinical Trial

Before releasing medications and other treatments to the public, researchers test them on a sample of patients. If this sample size is too small, researchers may not see results, or the results might be due to chance. The larger the sample size, the better the chances of seeing meaningful results and tracking correlations in a study. However, obtaining a large sample can be costly and difficult. You can use an equation to find the ideal minimum sample size to move forward with a credible clinical trial.

Instructions

• 1

  Decide on a significance level for the trial. When the probability of the null hypothesis is less than or equal to the significance level, you can reject the null hypothesis. This means the results of the study are valid, and not due to chance. The most commonly used significance levels are 0.05 and 0.01.

• 2

  Plug the significance level as an integer into the following equation: Significance level = 1/square root of N. N is the ideal minimum sample size. You can rearrange the equation like this:

  (significance level)*(square root of N) = 1.

  square root of N = 1/significance level

  N = 1/(significance level ^2)

• 3

  Solve the equation. For our example, the significance level will be 0.05:

  N = 1/(0.01^2) = 10,000 = 400.

  A credible study with a five percent margin of error requires a sample size of 400.