Sample size matters: A step-by-step guide for radiologists.

Abstract

Sample size is an essential step in any research study because it directly affects precision and statistical power. This article describes the main factors that determine the number of observations needed (power of a hypothesis test, significance criterion, minimum expected difference, variability, and asymmetry of the hypothesis test) and techniques for minimizing these factors. Our paper clearly presents examples of sample size calculations in radiology related to descriptive (mean and proportion) and comparative (two means, two proportions, intraclass correlations, and analysis of variance) studies. These examples are solved both manually and computationally using free R-based software.