In a recent paper, Laska, Meisner and Siegel address issues concerning hypothesis testing in cost-effectiveness analysis. They relate the relative magnitude of two average cost-effectiveness ratios to the incremental cost-effectiveness ratio and go on to propose a statistical procedure for testing the equality of two average ratios. In this paper, we show why the use of average cost-effectiveness ratios is misleading and argue that the appropriate focus for cost-effectiveness analysis is the estimation of confidence intervals around incremental cost-effectiveness ratios.