What Is Confidence? Part 1: The Use and Interpretation of Confidence Intervals

Abstract

Hypothesis testing and the P value it generates are overemphasized in statistical analyses published in medical journals. An alternative, the confidence interval (CI), offers significantly more information to readers interpreting results. There have been many authoritative calls for the report of CIs in place of P values,1-7 such as that of the International Committee of Medical Journal Editors, whose guidelines for statistical reporting give the following instructions: “When possible, quantify findings and present them with appropriate indicators of measurement error or uncertainty (such as confidence intervals),” and “Avoid sole reliance on statistical hypothesis testing, such as the use of P values, which fails to convey important quantitative information.”8 In this article, part 1, we provide an overview of CIs for the clinician reading the medical literature. We describe the advantages of CIs and explain and illustrate their proper interpretation. In part 2, which follows this article, we provide added information important for clinical researchers, including a precise definition of CIs, a compact reference to methods for calculating CIs in common situations, and an explanation of the difference between CIs and probability intervals.9 [Young KD, Lewis RJ: What is confidence? Part 1: The use and interpretation of confidence intervals. Ann Emerg Med September 1997;30:307-310.]