Stochastic league tables: communicating cost-effectiveness results to decision-makers

Abstract

The presentation of the results of uncertainty analysis in cost-effectiveness analysis (CEA) in the literature has been relatively academic with little attention paid to the question of how decision-makers should interpret the information particularly when confidence intervals overlap. This question is especially relevant to sectorial CEA providing information on the costs and effects of a wide range of interventions. This paper introduces stochastic league tables to inform decision-makers about the probability that a specific intervention would be included in the optimal mix of interventions for various levels of resource availability, taking into account the uncertainty surrounding costs and effectiveness. This information helps decision-makers decide on the relative attractiveness of different intervention mixes, and also on the implications for trading gains in efficiency for gains in other goals such as reducing health inequalities and increasing health system responsiveness.