A primer on confidence intervals in psychopharmacology

Abstract

Research papers and research summaries frequently present results in the form of data accompanied by 95% confidence intervals (CIs). Not all students and clinicians know how to interpret CIs. This article provides a nontechnical, nonmathematical discussion on how to understand and glean information from CIs; all explanations are accompanied by simple examples. A statistically accurate explanation about CIs is also provided. CIs are differentiated from standard deviations, standard errors, and confidence levels. The interpretation of narrow and wide CIs is discussed. Factors that influence the width of a CI are listed. Explanations are provided for how CIs can be used to assess statistical significance. The significance of overlapping and nonoverlapping CIs is considered. It is concluded that CIs are far more informative than, say, mere P values when drawing conclusions about a result.