Statistical significance versus clinical relevance. Part III. Methods for calculating confidence intervals

Formulae for calculating confidence intervals for different types of studies and conditions are presented. These include means, proportions, difference in means and proportions for paired and unpaired data, more complicated analyses of variance, medians, quantiles, relative risks (odd ratios), standardised ratios and rates, intercepts, slopes and correlation coefficients in regression and correlation analyses, as well as survival proportions calculated in survival analysis. For less frequently used formulae, examples are included.