EN
The analysis of the incremental cost-effectiveness ratio (ICER) is an important part of the social and health decision-making process, because ICER is used to obtain simultaneous information on the cost and effectiveness of a new intervention when compared to another one. Despite the increasing use of the ICER, studies on its statistical methodology have still not been sufficiently developed. In particular, the calculation of the confidence interval for the ICER is fundamental to take into account the uncertainty due to differences in samples. In this paper, a new parametric technique for the construction of confidence intervals for the ICER is proposed. It is based on the distribution of the ratio of two correlated normal variables. The method discussed has always existed, despite the degenerate cases of the classical parametric method proposed by Fieller, for which the classical region is not an interval. The computation of the confidence intervals proposed in the present paper may also be achieved in a feasible way.