OBJECTIVES: In probabilistic sensitivity analysis of a cost-effectiveness (CE) study, the unknown parameters, like transition probabilities, are considered random variables. A crucial question is what probabilistic distribution is suitable as synthesizing the available information (mainly data from clinical trials) about these parameters. In this context, it has been recognized the important role of the Bayesian methodology, under which, the parameters are of random nature. Despite the great appealing of the Bayesian approach to probabilistic sensitivity analysis, the ``lack of objectivity'' has been frequently argued as the main issue precluding the adoption of Bayesian techniques. This legitime concern has inspired the development of formal objective priors over the last decades. These priors are obtained as the result of mathematical formal rules applied to the models at hand and lead to Bayesian analyses influenced only by the data at hand. Formal objective priors have a number of appealing properties, including excellent frequentist behaviour. We explore, in the context of CE analyses, how formal objective Bayesian methods can be implemented. Specifically, we consider two problems that frequently appear in the CE literature: survival analysis and meta-analysis. We describe in detail the numerical methods that needs to be used to obtain the results. The methodology is fully illustrated using two CE analysis published in the literature. We compare our results with those obtained with other approaches to probabilistic sensitivity analysis. We conclude that the differences, when compared with other approaches, can be quite quite marked, specially when the number of patients enrolled in the simulated cohort under study is large.