[Normal confidence interval for a summary measure].

Abstract

This paper proposes an approach for calculating the normal confidence interval of a weighted summary measure which requires a particular continuous transformation for its variance estimation. By using the transformation properties and applying the delta method, the variance of transformed measure is easily expressed in terms of the transformed specific measure variances and the squared weights. The confidence limits of the summary measure are easily deduced by inverse transformation of those of transformed measure. The method is illustrated by applying it to some well known epidemiological measures. It seems appropriate for application in stratified analysis context where size allows normal approximation.