Bayesian methods in Cost-Effectiveness studies: Objectivity, Computation and other relevant aspects C. Armero, G. Garc´ ıa-Donato and A. L´opez-Qu´ ılez Universitat de Valencia and Universidad de Castilla-La Mancha (Spain) November 12, 2007 Abstract In a probabilistic sensitivity analysis of a cost-effectiveness (CE) study, the unknown parameters are considered as random variables. A crucial question is what probabilistic distribution is suitable for synthesizing the available informa- tion (mainly data from clinical trials) about these parameters. In this context, the important role of Bayesian methodology has been recognized, under which the pa- rameters are of a random nature. We explore, in the context of CE analyses, how formal objective Bayesian methods can be implemented. We fully illustrate the methodology using two CE problems that frequently appear in CE literature. The results are compared with those obtained with other popular approaches to prob- abilistic sensitivity analysis. We find that the discrepancies can be quite marked, specially when the number of patients enrolled in the simulated cohort under study is large. Finally, we describe in detail the numerical methods that need to be used to obtain the results. Keywords: Cost-effectiveness studies; Objective Bayesian methods; Probabilistic Sensi- tivity analysis. 1 Introduction Cost-effectiveness (CE) analysis is a methodology developed to compare two or more al- ternative treatments, explicitly taking into account the costs and consequences of each. In this context, the important role of Bayesian methods has been recognized, particularly in the analysis of the robustness of the responses of CE studies to variations in the inputs (Briggs, 2000; Berger et al., 2003; Weinstein et al., 2003). The main reason for this popu- larity is that the Bayesian technique perfectly accommodates the scheme of probabilistic sensitivity analysis (PSA) in which the variation, due to the imperfect knowledge of the 1