Increasingly, surgical research articles are citing confidence intervals (CIs) when reporting treatment effects. It is important to understand the theory behind CIs so that present and future surgical literature can be correctly interpreted and clinically useful information gained to help guide treatment decisions. The move toward including CIs is predominantly owing to them providing more information for the clinician regarding research results. In general, with p values, research results can be deemed statistically significant or not, whereas treatment effect and its corresponding CIs can give information regarding the magnitude of the difference between 2 treatments and the interval of values within which the true value is likely to be found.1 This provides information as to whether results are clinically important.2 To illustrate how CIs work, how to interpret them and how to critically appraise the validity of evidence using CIs of a treatment effect, a surgical problem and the critical appraisal of research findings are presented in this article.
展开▼
